© 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. 90685
    Prev
    Next
    INDEX
    Explanations

    Gordon Freeman

    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
     prodotti
    0.83
    িত
    0.75
    ༦
    0.74
    يد
    0.73
    ENT
    0.72
    يدا
    0.71
     براي
    0.71
     amend
    0.69
     agonist
    0.67
    ));
    0.66
    POSITIVE LOGITS
    al
    0.79
    p
    0.77
    ires
    0.69
    ifying
    0.68
    izing
    0.68
    as
    0.66
    ings
    0.66
    aways
    0.64
    ando
    0.63
    rom
    0.63
    Activations Density 0.000%

    No Known Activations