© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87076
    Prev
    Next
    INDEX
    Explanations

    cpp code includes

    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
    ش
    1.19
    0
    0.84
    ும்
    0.80
    ка
    0.74
    าล
    0.72
    ิก
    0.70
     domicile
    0.70
     dynamite
    0.70
     имат
    0.70
     domenica
    0.68
    POSITIVE LOGITS
    y
    0.72
    p
    0.72
    á
    0.71
    de
    0.71
     I
    0.67
     can
    0.65
    inent
    0.64
    ad
    0.62
     Qo
    0.62
    le
    0.61
    Activations Density 0.000%

    No Known Activations