© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90351
    Prev
    Next
    INDEX
    Explanations

    say h

    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_60_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
    ded
    0.51
    dır
    0.49
    zten
    0.48
    dte
    0.47
    нди
    0.46
    ﺪ
    0.45
    dı
    0.44
    τισ
    0.44
    dze
    0.43
    dy
    0.43
    POSITIVE LOGITS
    hi
    0.62
    house
    0.62
    hu
    0.61
    ha
    0.61
    how
    0.60
    H
    0.60
    HI
    0.59
    HIT
    0.59
    har
    0.58
    HAR
    0.58
    Activations Density 0.000%

    No Known Activations