© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204128
    Prev
    Next
    INDEX
    Explanations

    coded identifiers

    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
    us
    1.04
    _
    0.99
    c
    0.98
    and
    0.96
    a
    0.93
    d
    0.93
    ದ
    0.93
    ای
    0.91
    XA
    0.90
    }
    0.85
    POSITIVE LOGITS
    il
    0.91
    ми
    0.87
    hi
    0.85
    </strong>
    0.82
    ir
    0.80
    ன்
    0.80
    ной
    0.79
    </h3>
    0.79
    han
    0.78
     are
    0.77
    Activations Density 0.000%

    No Known Activations