© 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. 133988
    Prev
    Next
    INDEX
    Explanations

    scholars

    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
    ig
    0.80
    igungen
    0.80
    were
    0.79
    wes
    0.78
    ٣
    0.75
    luit
    0.74
    a
    0.74
    ᱗
    0.73
    woman
    0.72
     demande
    0.72
    POSITIVE LOGITS
    า
    1.10
    س
    1.01
    ı
    0.98
    ী
    0.98
    ת
    0.95
    as
    0.92
    ة
    0.89
    ం
    0.86
    ла
    0.85
    와의
    0.83
    Activations Density 0.000%

    No Known Activations