© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93308
    Prev
    Next
    INDEX
    Explanations

    A initial

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ه
    1.13
    a
    1.06
    ה
    0.75
    ा
    0.73
    া
    0.70
    ați
    0.69
    aing
    0.68
    aib
    0.63
    aun
    0.56
    ు
    0.55
    POSITIVE LOGITS
    A
    2.19
    AID
    0.86
    AAD
    0.82
    AAC
    0.80
    AUG
    0.78
    ACO
    0.75
    AUR
    0.74
    AED
    0.73
    AFF
    0.68
    А
    0.66
    Activations Density 0.068%

    No Known Activations