© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132404
    Prev
    Next
    INDEX
    Explanations

    objectivity

    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_1_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
     for
    2.14
    for
    1.64
    0
    1.55
     of
    1.19
    3
    1.16
    ни
    1.10
    i
    1.09
    <0x80>
    1.08
     by
    1.06
    রা
    1.03
    POSITIVE LOGITS
    ON
    0.98
     on
    0.96
    కి
    0.90
    क
    0.84
    お
    0.82
    見
    0.82
    ك
    0.81
    も
    0.79
    出
    0.79
    ስቃ
    0.78
    Activations Density 0.000%

    No Known Activations