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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13322
    Prev
    Next
    INDEX
    Explanations

    phrases expressing suggestions or possibilities

    oai_token-act-pair · gemini-2.0-flash

    possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Réponses
    -0.77
    Autoritní
    -0.77
    SharedDtor
    -0.75
    ftagPool
    -0.75
    BagConstraints
    -0.72
    Panamoan
    -0.72
    UnsafeEnabled
    -0.71
     doInBackground
    -0.71
     estekak
    -0.68
    tanleria
    -0.68
    POSITIVE LOGITS
     being
    0.48
     rem
    0.42
    <bos>
    0.42
    ind
    0.41
     Se
    0.41
     applied
    0.41
    se
    0.41
     Hark
    0.41
    all
    0.40
    ser
    0.40
    Activations Density 2.082%

    No Known Activations