© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3104
    Prev
    Next
    INDEX
    Explanations

    snippets of code containing assignment and appending operations

    oai_token-act-pair · gemini-2.0-flash

    scientific code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     plus
    -2.53
     +
    -2.30
    plus
    -2.16
    +
    -2.16
     плюс
    -2.08
     Plus
    -2.05
     PLUS
    -2.02
     $+$
    -2.00
     $+
    -1.94
    Plus
    -1.93
    POSITIVE LOGITS
    "]="
    0.50
    </tfoot>
    0.49
     dejes
    0.44
    )}</
    0.44
    égard
    0.44
    )‏
    0.43
    tili
    0.42
    脚注の使い方
    0.42
    ))->
    0.41
    [/
    0.40
    Activations Density 2.737%

    No Known Activations