© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111567
    Prev
    Next
    INDEX
    Explanations

    bogged down in

    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_2_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
     up
    1.26
     in
    1.20
    ing
    1.14
    att
    1.04
     at
    1.02
    ast
    1.02
    ة
    1.02
     an
    0.91
    ą
    0.84
    ض
    0.84
    POSITIVE LOGITS
    し
    1.35
    א
    1.29
    l
    1.24
    おしゃれ
    1.20
    dır
    1.16
    has
    1.13
    면에
    1.13
    した
    1.12
    I
    1.12
    ll
    1.10
    Activations Density 0.000%

    No Known Activations