© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15880
    Prev
    Next
    INDEX
    Explanations

    programming questions asking for help

    oai_token-act-pair · gemini-2.0-flash

    someone/somebody

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AndEndTag
    -0.71
     endfor
    -0.60
    脚注の使い方
    -0.60
    yntaxException
    -0.58
    localctx
    -0.54
    ">',
    -0.52
    ("'"
    -0.51
     Popis
    -0.49
     andato
    -0.49
     InkWell
    -0.49
    POSITIVE LOGITS
     someone
    2.88
    someone
    2.73
     somebody
    2.63
    Someone
    2.61
     Someone
    2.56
    somebody
    2.36
     Somebody
    2.27
    Somebody
    2.23
     SOMEONE
    2.20
     alguien
    2.06
    Activations Density 2.740%

    No Known Activations