© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6402
    Prev
    Next
    INDEX
    Explanations

    descriptions of positional relationships.

    oai_token-act-pair · gemini-2.0-flash

    Spatial positions

    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
     виправивши
    -1.08
    MigrationBuilder
    -1.04
    GEBURTSDATUM
    -1.03
     Италијани
    -0.97
    IVEREF
    -0.94
    LookAnd
    -0.92
     ModelExpression
    -0.92
    AndroidJUnit
    -0.91
    الإنجليزية
    -0.90
     iſt
    -0.89
    POSITIVE LOGITS
    ecore
    0.47
    ,
    0.45
    .
    0.43
     of
    0.42
     (
    0.39
    -
    0.35
    /
    0.35
     on
    0.35
    -,
    0.35
     leg
    0.34
    Activations Density 4.471%

    No Known Activations