© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129965
    Prev
    Next
    INDEX
    Explanations

    totally + [adjective/adverb]

    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
    会
    1.51
    ется
    1.41
    ről
    1.34
    去
    1.33
    માં
    1.24
    ق
    1.24
    ے
    1.24
    on
    1.23
    ع
    1.19
    ă
    1.16
    POSITIVE LOGITS
    '
    0.90
     Wasn
    0.83
    OWER
    0.80
    <unused2030>
    0.78
    '.
    0.77
    termilk
    0.77
    را
    0.76
    rien
    0.76
    AV
    0.75
    mathbf
    0.75
    Activations Density 0.000%

    No Known Activations