© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38252
    Prev
    Next
    INDEX
    Explanations

    start or end turn

    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_57_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
     )-
    0.38
    "--
    0.34
    )–
    0.33
    dey
    0.31
    oue
    0.31
    Pov
    0.31
    lymp
    0.30
    rhein
    0.30
    ="-
    0.29
    玦
    0.29
    POSITIVE LOGITS
     THEY
    0.37
     HOWEVER
    0.35
     THESE
    0.34
     diesen
    0.31
     ইহার
    0.31
     THERE
    0.31
    BUT
    0.31
     MANY
    0.31
     MARKET
    0.30
     SOME
    0.30
    Activations Density 0.000%

    No Known Activations