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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8919
    Prev
    Next
    INDEX
    Explanations

    content related to deception and control

    oai_token-act-pair · gemini-2.0-flash

    senses

    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
    TypedDataSet
    -0.59
     Survive
    -0.54
     count
    -0.54
     read
    -0.54
    STARTING
    -0.54
    Writes
    -0.53
     listen
    -0.52
    DropTable
    -0.52
     stand
    -0.51
     Listen
    -0.51
    POSITIVE LOGITS
     seeing
    0.70
     hearing
    0.64
     Seeing
    0.57
     reading
    0.56
     nakalista
    0.55
     knowing
    0.54
     estekak
    0.54
     loving
    0.52
     Hearing
    0.52
    DatabaseError
    0.51
    Activations Density 11.890%

    No Known Activations