© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138533
    Prev
    Next
    INDEX
    Explanations

    fingerprint

    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
     игры
    0.60
     لاءِ
    0.54
     людей
    0.54
     книги
    0.53
     jeux
    0.52
     Karp
    0.52
     dalších
    0.52
    釷
    0.52
    as
    0.50
     Nous
    0.50
    POSITIVE LOGITS
    HttpMessage
    0.56
    ToJava
    0.52
     porcelain
    0.50
    lire
    0.50
    TEE
    0.50
    ♒
    0.50
    PhoneNumber
    0.49
     hypnotic
    0.49
    reat
    0.49
    cssMode
    0.48
    Activations Density 0.000%

    No Known Activations