© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60725
    Prev
    Next
    INDEX
    Explanations

    US followed by punctuation or AI

    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_2_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
    ார்
    0.96
    েরও
    0.95
    u
    0.92
    те
    0.89
    りたい
    0.87
    ,
    0.87
    KM
    0.86
    UserID
    0.85
    ác
    0.84
    IS
    0.84
    POSITIVE LOGITS
    ።
    1.72
    n
    1.71
    .
    1.66
    ۔
    1.59
    ។
    1.56
    ।
    1.27
    ت
    1.20
    ။
    1.19
    ید
    1.15
    iy
    1.11
    Activations Density 0.000%

    No Known Activations