© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11777
    Prev
    Next
    INDEX
    Explanations

    government bodies and their decisions.

    oai_token-act-pair · gemini-2.0-flash

    government/board decisions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    SourceChecksum
    -0.70
     Cæsar
    -0.64
     Wab
    -0.64
     HasFactory
    -0.64
    Geplaatst
    -0.60
     actionTypes
    -0.60
    脚注の使い方
    -0.59
     buns
    -0.58
    <bos>
    -0.58
     habet
    -0.58
    POSITIVE LOGITS
    bootstrapcdn
    0.51
     dead
    0.50
    dead
    0.48
     CONSIDER
    0.47
     consider
    0.46
     propOrder
    0.45
    cast
    0.45
     stimm
    0.44
     TableColumn
    0.44
     Dead
    0.43
    Activations Density 3.070%

    No Known Activations