© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250286
    Prev
    Next
    INDEX
    Explanations

    blog

    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
    s
    0.85
    ের
    0.72
    ی
    0.60
    ों
    0.57
    ים
    0.53
    ો
    0.49
    ओं
    0.45
    sning
    0.45
    ség
    0.43
    ς
    0.41
    POSITIVE LOGITS
    gers
    0.41
    gery
    0.41
    ging
    0.39
    gy
    0.38
    гом
    0.38
    ড়ানো
    0.37
    γή
    0.36
    gina
    0.35
     ss
    0.34
    ביע
    0.34
    Activations Density 0.000%

    No Known Activations