© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6658
    Prev
    Next
    INDEX
    Explanations

    windows 10

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    و
    0.75
    р
    0.68
    ்ச
    0.65
    sofar
    0.64
    о
    0.63
    na
    0.63
    st
    0.62
    r
    0.60
    }$)
    0.59
    ている
    0.59
    POSITIVE LOGITS
    minLength
    0.80
    い
    0.75
    ের
    0.73
    ER
    0.69
    ிறது
    0.67
    िक
    0.66
    न
    0.66
    د
    0.65
     thước
    0.65
     exibir
    0.64
    Activations Density 0.004%

    No Known Activations