© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110810
    Prev
    Next
    INDEX
    Explanations

    KENJI, SATO, FENIXFOOD, BASENJI

    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
    }",
    1.32
    이지만
    1.25
    4
    1.20
    3
    1.16
    .".
    1.06
    ことができる
    1.06
     avete
    1.04
    5
    1.04
    も含
    1.03
    ש
    1.02
    POSITIVE LOGITS
    '
    2.47
    s
    2.27
    er
    1.74
    h
    1.59
    t
    1.57
    m
    1.51
    te
    1.47
     is
    1.44
    ing
    1.39
    en
    1.38
    Activations Density 0.001%

    No Known Activations