© 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. 134176
    Prev
    Next
    INDEX
    Explanations

    sorption

    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
     а
    1.08
    .
    1.08
    ке
    1.02
    9
    0.99
    miri
    0.97
     або
    0.96
     extin
    0.94
    ."},
    0.94
     anteriores
    0.94
    mato
    0.93
    POSITIVE LOGITS
    त
    1.52
     on
    1.45
    č
    1.38
    il
    1.35
    т
    1.31
    ت
    1.30
    ł
    1.27
    ın
    1.27
    ع
    1.25
    ad
    1.21
    Activations Density 0.000%

    No Known Activations