© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39408
    Prev
    Next
    INDEX
    Explanations

    stories and ideas

    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
    ക്കേ
    0.38
    にとって
    0.37
    的双
    0.37
    }=
    0.36
     diseños
    0.36
    的设计
    0.36
     probing
    0.35
    dib
    0.35
     ведь
    0.35
     amps
    0.34
    POSITIVE LOGITS
    ’
    0.73
    '
    0.59
    ❜
    0.55
    ʼ
    0.47
    ʿ
    0.45
    ʻ
    0.42
    ʾ
    0.39
    чис
    0.39
    nous
    0.39
    ドド
    0.38
    Activations Density 0.008%

    No Known Activations