© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23839
    Prev
    Next
    INDEX
    Explanations

    word parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    shaft
    0.46
    তা
    0.46
    ar
    0.41
    s
    0.37
    ingly
    0.37
    lessly
    0.37
    arang
    0.36
    ship
    0.36
    ্মান
    0.34
     দলটি
    0.34
    POSITIVE LOGITS
    y
    0.49
    icoli
    0.38
    on
    0.36
     Cras
    0.36
    पृ
    0.36
     argentina
    0.35
    ters
    0.35
     walker
    0.35
    illante
    0.35
    munic
    0.33
    Activations Density 0.036%

    No Known Activations