© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201411
    Prev
    Next
    INDEX
    Explanations

    CDMA codes

    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_12_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
    عت
    0.55
    阉
    0.52
     UHD
    0.51
    ీయ
    0.51
     عند
    0.51
    हत
    0.50
    iscuit
    0.50
     između
    0.50
    सँग
    0.50
    ：%
    0.50
    POSITIVE LOGITS
    job
    0.59
    error
    0.57
    ones
    0.56
    როს
    0.56
    mortar
    0.56
    allow
    0.56
    filtr
    0.55
    possible
    0.55
    aren
    0.54
    fuzzy
    0.54
    Activations Density 0.000%

    No Known Activations