© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86565
    Prev
    Next
    INDEX
    Explanations

    available to the public

    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_23_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
    ಾರು
    0.37
    قق
    0.36
    시
    0.34
    Statement
    0.34
    ArrayIndex
    0.34
    olari
    0.33
    产品
    0.33
    уда
    0.33
     malay
    0.33
    阵
    0.33
    POSITIVE LOGITS
    imacy
    0.49
    rases
    0.44
    aneity
    0.42
    liferation
    0.41
     ဆို
    0.40
     حاول
    0.40
    raseña
    0.39
     preferencia
    0.39
    entieth
    0.39
     dicen
    0.38
    Activations Density 0.007%

    No Known Activations