© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124006
    Prev
    Next
    INDEX
    Explanations

    moonbeam

    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_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
    ی
    0.89
    ش
    0.81
    स
    0.79
    보
    0.77
    ש
    0.76
     esperti
    0.75
    ב
    0.74
    ч
    0.73
    ской
    0.73
    ید
    0.71
    POSITIVE LOGITS
    ul
    0.71
    uk
    0.70
    uh
    0.68
    iu
    0.64
    im
    0.63
    aking
    0.62
    uv
    0.61
    ie
    0.61
    int
    0.61
    ac
    0.59
    Activations Density 0.001%

    No Known Activations