© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10674
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, criminal activity, positions of power and departure or movement.

    oai_token-act-pair · gemini-2.0-flash

    departure

    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
    expandindo
    -1.10
     BoxFit
    -0.98
    WebVitals
    -0.98
     GenerationType
    -0.97
     AttributeSet
    -0.95
     HasFactory
    -0.93
     MotionEvent
    -0.91
    GenerationType
    -0.91
    istoitu
    -0.88
     serpents
    -0.88
    POSITIVE LOGITS
     the
    0.83
     it
    0.71
     of
    0.68
     that
    0.67
     you
    0.64
     your
    0.64
     also
    0.64
     and
    0.63
     with
    0.63
    ,
    0.63
    Activations Density 1.478%

    No Known Activations