© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85550
    Prev
    Next
    INDEX
    Explanations

    vertical lines and strokes

    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
     действия
    0.69
     carcasses
    0.63
    els
    0.59
    〉
    0.58
    ites
    0.58
    itus
    0.58
     disordered
    0.58
     procent
    0.57
    дин
    0.57
     degrés
    0.57
    POSITIVE LOGITS
    t
    1.20
    ת
    0.88
    ت
    0.82
     I
    0.77
    },
    0.69
    ა
    0.68
    </h4>
    0.64
    n
    0.64
    nThe
    0.63
    nA
    0.62
    Activations Density 0.003%

    No Known Activations