© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16213
    Prev
    Next
    INDEX
    Explanations

    instances of the word "side" or hyphenated words describing time, fitness or the user

    oai_token-act-pair · gemini-2.0-flash

    say by

    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
    MigrationBuilder
    -1.20
    LookAnd
    -1.16
     Мексичка
    -1.14
     autorytatywna
    -1.09
     resourceCulture
    -1.07
    原始内容存档于
    -1.07
    })*/
    -1.05
     Roskov
    -1.03
    MarshalTo
    -1.02
     ModelExpression
    -0.99
    POSITIVE LOGITS
     by
    0.44
     k
    0.42
     to
    0.41
     i
    0.37
     segments
    0.35
    kk
    0.35
    --
    0.33
     segment
    0.33
     K
    0.33
     ninety
    0.33
    Activations Density 1.699%

    No Known Activations