© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3295
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with possibility, permission, obligation, and desire

    oai_token-act-pair · gemini-2.0-flash

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -1.27
    <eos>
    -0.44
    ’
    -0.42
     Tuch
    -0.40
    Azur
    -0.39
    例文帳に追加
    -0.39
    '
    -0.37
    IO
    -0.36
    chin
    -0.36
     amp
    -0.35
    POSITIVE LOGITS
     Theſe
    0.67
     Majefty
    0.67
     ſtate
    0.64
     Monfieur
    0.63
     themſelves
    0.63
    ^(@)
    0.62
     becauſe
    0.62
     himſelf
    0.59
     purpoſe
    0.59
    NUMX
    0.59
    Activations Density 2.838%

    No Known Activations