© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88660
    Prev
    Next
    INDEX
    Explanations

    Selina Kyle, Cancun, Gomez

    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_3_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
    అ
    0.64
     опа
    0.63
    إ
    0.61
     челу
    0.61
    ني
    0.61
     vòng
    0.60
     obra
    0.59
     seaside
    0.59
     θέση
    0.59
     efectuar
    0.59
    POSITIVE LOGITS
    f
    0.89
    ग्न
    0.73
    er
    0.71
    c
    0.70
    ע
    0.68
    h
    0.67
    p
    0.66
    ان
    0.66
    ﺀ
    0.65
    ма
    0.64
    Activations Density 0.000%

    No Known Activations