© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38100
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    im
    0.80
    imen
    0.69
    ir
    0.66
    ime
    0.66
    ih
    0.66
    ige
    0.66
    igal
    0.64
    ि
    0.63
    ild
    0.63
    irt
    0.63
    POSITIVE LOGITS
    াম্প
    0.43
    ෙක්
    0.39
    Ꮼ
    0.38
    enne
    0.38
    ChildScrollView
    0.38
    ence
    0.37
     Anthem
    0.37
    AES
    0.37
    esseur
    0.36
    adem
    0.35
    Activations Density 0.071%

    No Known Activations