© 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. 232084
    Prev
    Next
    INDEX
    Explanations

    important to remember que

    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
    С
    1.16
    К
    1.05
     they
    1.00
     not
    0.98
    IE
    0.95
    _
    0.93
    の頃
    0.93
    <?
    0.88
    <
    0.87
    Q
    0.87
    POSITIVE LOGITS
     isomerization
    0.86
     fáb
    0.82
     mít
    0.79
    ون
    0.77
    يلي
    0.77
     synapses
    0.77
     две
    0.77
     четы
    0.77
     అభి
    0.76
    ب
    0.76
    Activations Density 0.000%

    No Known Activations