© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46245
    Prev
    Next
    INDEX
    Explanations

    banks, temples, institutions

    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_13_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
     созда
    0.47
     нај
    0.46
     wets
    0.46
     pře
    0.44
     n
    0.43
     naj
    0.42
     drape
    0.42
    డవ
    0.42
     firstname
    0.42
     भुला
    0.42
    POSITIVE LOGITS
    '
    0.50
    Policy
    0.44
    on
    0.44
    BER
    0.41
    ப
    0.41
    tool
    0.40
    Marg
    0.40
    field
    0.40
    \(
    0.40
    M
    0.40
    Activations Density 0.022%

    No Known Activations