© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229420
    Prev
    Next
    INDEX
    Explanations

    art of / kinds of

    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_6_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
    in
    1.20
    mentation
    1.07
    em
    1.06
    ens
    1.06
    "
    1.04
    س
    1.00
    ry
    1.00
    ست
    0.97
    ot
    0.96
    ار
    0.96
    POSITIVE LOGITS
     mantém
    1.05
    ุ
    1.02
     différent
    1.01
     rů
    1.01
    я
    0.97
     tari
    0.96
     pozy
    0.95
     minore
    0.95
     społecz
    0.94
     wspól
    0.94
    Activations Density 0.001%

    No Known Activations