© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150976
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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_59_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
    滙
    0.42
    delicious
    0.40
    Denne
    0.39
    imps
    0.39
    dropping
    0.38
    Hvis
    0.38
    ဤ
    0.37
    my
    0.36
    र्वे
    0.36
    बारा
    0.36
    POSITIVE LOGITS
     OFF
    0.63
     Off
    0.52
     Volume
    0.52
     Vol
    0.52
     VOLUME
    0.50
     VOL
    0.49
     IN
    0.48
     Published
    0.47
     B
    0.47
     TICK
    0.46
    Activations Density 0.000%

    No Known Activations