© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49305
    Prev
    Next
    INDEX
    Explanations

    flow and release

    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_31_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
     Deposits
    0.40
    糀
    0.39
     extracting
    0.38
    extract
    0.37
    SCREEN
    0.36
    Depos
    0.36
     extract
    0.35
    rect
    0.35
    klad
    0.35
     extractor
    0.35
    POSITIVE LOGITS
     Fluss
    0.49
     fluvial
    0.42
     river
    0.40
     downstream
    0.40
     пото
    0.39
     entailed
    0.39
    河
    0.38
    河流
    0.37
     Seine
    0.37
     aliran
    0.36
    Activations Density 0.023%

    No Known Activations