© 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. 107600
    Prev
    Next
    INDEX
    Explanations

    are followed by negations or comparisons

    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
    お
    1.29
    این
    1.26
    した
    1.18
    д
    1.13
    د
    1.13
    یت
    1.12
    িয়ে
    1.11
     அளிக்க
    1.09
    때
    1.06
    ても
    1.05
    POSITIVE LOGITS
    et
    1.12
    -
    1.08
    ↵
    1.02
    .
    1.01
    কে
    1.00
     I
    0.99
    ర్
    0.95
    ৭
    0.92
    ol
    0.90
    лис
    0.89
    Activations Density 0.016%

    No Known Activations