© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12601
    Prev
    Next
    INDEX
    Explanations

    mentions of facts, materials, whether something is better than something else, and people who are not me.

    oai_token-act-pair · gemini-2.0-flash

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.52
     myſelf
    -1.47
     themſelves
    -1.43
     greateſt
    -1.41
     himſelf
    -1.40
     Monfieur
    -1.38
     Reſ
    -1.37
     Anſ
    -1.34
     Jefus
    -1.33
    ſelves
    -1.30
    POSITIVE LOGITS
    <bos>
    0.72
    .
    0.54
     olarak
    0.54
     vs
    0.52
     v
    0.50
    ,
    0.49
     («
    0.49
     intende
    0.49
    ’
    0.48
     ciertos
    0.48
    Activations Density 1.063%

    No Known Activations