© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88544
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    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_23_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
     오류
    0.51
    ല്ല
    0.45
     형
    0.44
     кри
    0.43
     музе
    0.42
    కే
    0.40
     tajem
    0.40
    لاش
    0.39
     세계
    0.39
     점
    0.39
    POSITIVE LOGITS
     weekly
    0.40
     tremendous
    0.39
     twice
    0.38
    Results
    0.37
    ayos
    0.37
     Weeks
    0.36
    Save
    0.36
    Weekly
    0.35
    Weeks
    0.35
    wife
    0.35
    Activations Density 0.014%

    No Known Activations