© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122514
    Prev
    Next
    INDEX
    Explanations

    historically

    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_37_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
    ॉड
    0.41
     повин
    0.40
    Mé
    0.39
    Grpc
    0.38
     bowing
    0.38
     historischen
    0.38
    婼
    0.37
    mia
    0.37
     wig
    0.36
    mini
    0.36
    POSITIVE LOGITS
     було
    0.46
     સૌથી
    0.45
     كانوا
    0.44
    땠
    0.40
    하던
    0.40
     было
    0.39
     étaient
    0.38
     było
    0.38
     كانت
    0.37
    rentice
    0.37
    Activations Density 0.006%

    No Known Activations