© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37413
    Prev
    Next
    INDEX
    Explanations

    programming components

    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_57_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
    AOrdenar
    0.47
    abhuto
    0.47
     PLUGIN
    0.45
    करना
    0.44
    큼
    0.44
    antaranya
    0.44
    akkhati
    0.43
    한편
    0.41
    ковского
    0.40
     langchain
    0.40
    POSITIVE LOGITS
    -
    0.52
    e
    0.49
    а
    0.47
    i
    0.47
    a
    0.47
    aing
    0.46
    h
    0.46
    m
    0.46
    gery
    0.46
    room
    0.45
    Activations Density 0.022%

    No Known Activations