© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42376
    Prev
    Next
    INDEX
    Explanations

    Sequential models

    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_22_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
    Seat
    0.47
     मिड
    0.46
    )=-
    0.43
    :=
    0.43
    AssetDiscovery
    0.42
    Soc
    0.42
    Prop
    0.41
    Pick
    0.41
    ᓴ
    0.41
    विड
    0.41
    POSITIVE LOGITS
     otras
    0.46
    તાવ
    0.42
     grazie
    0.41
     Bulletin
    0.40
     Biotechnology
    0.40
     Grazie
    0.40
     dataGridView
    0.39
     Ста
    0.38
     Law
    0.38
     BAR
    0.38
    Activations Density 0.002%

    No Known Activations