© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12838
    Prev
    Next
    INDEX
    Explanations

    articles, proper nouns, words that suggest something important, and objective pronouns.

    oai_token-act-pair · gemini-2.0-flash

    archaic or unusual spellings

    np_token-act-pair-logits · gpt-4o-mini

    obscure or uncommon language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     (
    -0.59
     
    -0.57
     I
    -0.56
    ,
    -0.54
     A
    -0.54
     E
    -0.51
     -
    -0.50
     Ver
    -0.50
     "
    -0.49
    ?
    -0.48
    POSITIVE LOGITS
     myſelf
    1.23
     ―――――
    1.16
     iſt
    1.04
     itſelf
    1.02
     ſind
    1.02
     Eſ
    1.00
     Monfieur
    0.98
     dieß
    0.97
     raiſ
    0.95
     himſelf
    0.95
    Activations Density 6.811%

    No Known Activations