© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52205
    Prev
    Next
    INDEX
    Explanations

    word parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    C
    0.63
    Ei
    0.62
    A
    0.57
    S
    0.57
    E
    0.57
    Cv
    0.56
    R
    0.54
    D
    0.54
    Sd
    0.53
    M
    0.53
    POSITIVE LOGITS
    IFICATION
    0.45
    NOWLEDG
    0.42
    IFIED
    0.41
    ARRY
    0.38
    COUVER
    0.38
    ICK
    0.38
    ię
    0.36
    OPLE
    0.36
    LEMENT
    0.35
    IGATION
    0.35
    Activations Density 0.007%

    No Known Activations