© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13840
    Prev
    Next
    INDEX
    Explanations

    words related to fear, darkness, and horror

    oai_token-act-pair · gemini-2.0-flash

    Story excerpts or titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     >=",
    -0.91
    LookAnd
    -0.89
    enterOuterAlt
    -0.85
    sizeCache
    -0.80
    PreferredItem
    -0.77
    WriteBarrier
    -0.76
     Accesat
    -0.76
     Roskov
    -0.76
    HasAnnotation
    -0.74
     Paglinawan
    -0.74
    POSITIVE LOGITS
     Children
    0.49
    ственности
    0.49
    ,
    0.45
    :
    0.44
     to
    0.43
     Young
    0.43
    Children
    0.43
     God
    0.42
     in
    0.42
     and
    0.42
    Activations Density 3.343%

    No Known Activations