© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146316
    Prev
    Next
    INDEX
    Explanations

    alternative suggestions or clauses

    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_0_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
    and
    2.00
     and
    1.41
    ac
    1.36
    av
    1.22
    um
    1.20
    2
    1.17
    oc
    1.13
    ff
    1.13
    ная
    1.09
    ной
    1.09
    POSITIVE LOGITS
     in
    1.73
    お
    1.55
    ক
    1.46
    స
    1.43
    在
    1.41
    ิน
    1.38
     is
    1.35
    అ
    1.34
    Э
    1.33
    ان
    1.32
    Activations Density 0.001%

    No Known Activations