© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12043
    Prev
    Next
    INDEX
    Explanations

    pronouns and forms of "to be" in the present tense, along with words like 'eventually' and 'eventually', and some adjectives.

    oai_token-act-pair · gemini-2.0-flash

    words related to emotional and mental states

    np_token-act-pair-logits · gpt-4o-mini

    conversation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GroupLayout
    -0.59
     Wikiseite
    -0.59
    ValueGeneration
    -0.58
    unggulan
    -0.54
    ViewSet
    -0.51
     coscienza
    -0.51
    usters
    -0.50
    TypedDataSet
    -0.50
     cherchés
    -0.50
    astify
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.65
     influenced
    0.54
     ready
    0.52
     nahilalakip
    0.51
     drawn
    0.50
     obligated
    0.50
     attracted
    0.50
     affected
    0.50
     temporary
    0.49
    esez
    0.49
    Activations Density 1.373%

    No Known Activations