© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129685
    Prev
    Next
    INDEX
    Explanations

    nosis

    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_6_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
     });
    0.93
    Το
    0.90
     otras
    0.88
     το
    0.85
     offenen
    0.84
     لأ
    0.84
     increí
    0.82
    phe
    0.80
     والتي
    0.80
     Nachdem
    0.80
    POSITIVE LOGITS
    \
    1.00
    .
    0.97
    -
    0.93
    نا
    0.84
    िन
    0.79
    I
    0.76
     burglary
    0.75
    (
    0.75
     haircut
    0.72
    摖
    0.71
    Activations Density 0.001%

    No Known Activations