© 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. 138523
    Prev
    Next
    INDEX
    Explanations

    too + adjective

    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
    ia
    0.23
    ваме
    0.22
    灞
    0.20
    noduch
    0.20
    or
    0.20
     ய
    0.19
     გვ
    0.19
    StructOf
    0.19
    ropical
    0.19
     consortium
    0.19
    POSITIVE LOGITS
    U
    0.28
    In
    0.25
    У
    0.24
    J
    0.24
    O
    0.24
    Ook
    0.23
    Una
    0.23
    Complaint
    0.23
    도
    0.22
     offender
    0.22
    Activations Density 0.003%

    No Known Activations