© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    the words "said" and "discloses" when they are in close proximity

    oai_token-act-pair · gemini-2.0-flash

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ProtoMessage
    -0.97
    GEBURTSDATUM
    -0.93
    GraphicsUnit
    -0.89
    OGND
    -0.88
     дописавши
    -0.88
    awtextra
    -0.87
    DockStyle
    -0.85
     contextLoads
    -0.84
    NUMX
    -0.84
    دانشنامهٔ
    -0.84
    POSITIVE LOGITS
     Hered
    0.55
    amu
    0.49
     laman
    0.47
     výsled
    0.45
    dawnictwo
    0.44
    тербург
    0.44
    ess
    0.44
     майо
    0.44
    wuchs
    0.44
    ―
    0.44
    Activations Density 0.787%

    No Known Activations