© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83541
    Prev
    Next
    INDEX
    Explanations

    horizontally, horrible, horned

    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_0_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
    ó
    1.63
     It
    1.55
    та
    1.46
    ri
    1.41
    ut
    1.38
    and
    1.38
    s
    1.36
    ir
    1.33
    ی
    1.27
    ों
    1.24
    POSITIVE LOGITS
    ות
    1.41
     slew
    1.32
    .
    1.23
    ס
    1.23
     מת
    1.15
     monde
    1.14
    dır
    1.13
    لي
    1.13
    }$
    1.12
     הס
    1.11
    Activations Density 0.001%

    No Known Activations