© 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. 13043
    Prev
    Next
    INDEX
    Explanations

    complicated sentence structures using many conjunctions and auxiliary verbs and personal pronouns.

    oai_token-act-pair · gemini-2.0-flash

    statements

    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
    .
    -0.64
    :
    -0.57
    2
    -0.57
     
    -0.55
    f
    -0.53
    ,
    -0.53
    +
    -0.51
    (
    -0.50
    3
    -0.49
    ;
    -0.49
    POSITIVE LOGITS
     myſelf
    1.06
    NUMX
    1.04
     Majefty
    1.02
     estekak
    1.01
     Anſ
    0.98
     itſelf
    0.97
     Normdatei
    0.96
     للمعارف
    0.96
     Савезне
    0.94
    ########.
    0.94
    Activations Density 1.261%

    No Known Activations