© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136745
    Prev
    Next
    INDEX
    Explanations

    BIM API integration and parameters

    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
     Stalingrad
    0.54
     dayan
    0.53
     Ultrasound
    0.52
     \
    0.52
    ﺩ
    0.50
     accordance
    0.50
     tetapi
    0.50
     Cardinals
    0.49
    Ꮡ
    0.49
     superstars
    0.49
    POSITIVE LOGITS
    λη
    0.48
    ный
    0.47
    Ref
    0.47
    Each
    0.46
    od
    0.45
     Jalis
    0.45
    тного
    0.44
     ojo
    0.44
    オ
    0.44
    ные
    0.44
    Activations Density 0.015%

    No Known Activations