© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    first person pronouns followed by words of speaking or wanting.

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming and technical concepts

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

    giving/telling

    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
     me
    -2.02
     we
    -1.70
     us
    -1.59
     conmigo
    -1.26
     nous
    -1.23
    me
    -1.17
     мне
    -1.17
     conosco
    -1.16
    We
    -1.15
    we
    -1.14
    POSITIVE LOGITS
     ModelExpression
    0.94
    AddTagHelper
    0.93
     BoxFit
    0.93
     autorytatywna
    0.92
     NUKAT
    0.83
    Personensuche
    0.83
    rungsseite
    0.82
    extAlignment
    0.82
    GraphicsUnit
    0.79
    ImageContext
    0.76
    Activations Density 3.747%

    No Known Activations