© 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. 201173
    Prev
    Next
    INDEX
    Explanations

    file operations (`zip`, `cp`)

    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
    stuff
    0.46
    ercises
    0.40
    蔽
    0.39
     depict
    0.37
     depicts
    0.37
     Jon
    0.36
    sender
    0.35
    ပေး
    0.35
    抚
    0.35
    ित
    0.34
    POSITIVE LOGITS
    ConfigFile
    0.47
     imdb
    0.40
     파일을
    0.39
    ファイルを
    0.39
     returnValue
    0.39
     зло
    0.39
     violation
    0.38
    𝔞
    0.38
    imdb
    0.38
     lifeless
    0.37
    Activations Density 0.008%

    No Known Activations