© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201956
    Prev
    Next
    INDEX
    Explanations

    hashtags

    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_6_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
    re
    0.90
    le
    0.83
    enje
    0.82
    d
    0.81
    se
    0.78
    oi
    0.78
    ap
    0.75
    v
    0.75
    z
    0.75
    el
    0.74
    POSITIVE LOGITS
    -
    0.90
    {
    0.80
    0.75
    <
    0.72
    }(
    0.64
    ร
    0.63
    Nh
    0.62
    }()
    0.60
    น
    0.60
    يس
    0.58
    Activations Density 0.001%

    No Known Activations