© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    common words

    oai_token-act-pair · gemini-2.0-flash

    pronouns and reflexive actions

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

    pronouns

    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
     she
    -1.55
    she
    -1.31
    She
    -1.30
     She
    -1.17
    Она
    -1.03
    她
    -1.00
     она
    -1.00
    彼女は
    -1.00
     herself
    -0.98
     她
    -0.98
    POSITIVE LOGITS
     his
    0.72
     himſelf
    0.65
     GeoNames
    0.64
     JAXBElement
    0.63
     raiſ
    0.61
     themſelves
    0.60
     him
    0.58
     whoſe
    0.58
     ſtand
    0.58
     ſta
    0.57
    Activations Density 12.411%

    No Known Activations