© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225090
    Prev
    Next
    INDEX
    Explanations

    Providence and provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     broaden
    0.79
     وير
    0.76
     gắng
    0.75
    ᚄ
    0.74
    оны
    0.74
     Верх
    0.71
    }$.
    0.70
    }<
    0.70
    ONS
    0.70
     بير
    0.70
    POSITIVE LOGITS
    as
    1.23
    et
    1.06
    in
    0.96
    า
    0.89
    h
    0.87
    ia
    0.86
    f
    0.85
    i
    0.79
    us
    0.79
    ad
    0.79
    Activations Density 0.001%

    No Known Activations