© 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. 208002
    Prev
    Next
    INDEX
    Explanations

    Explanation

    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
     weaving
    0.41
    jal
    0.39
    :`
    0.38
     चली
    0.36
    WEI
    0.36
     বিয়ের
    0.35
     weaves
    0.35
    manam
    0.35
    ROLE
    0.35
    ְ
    0.35
    POSITIVE LOGITS
    emps
    0.37
     React
    0.36
     реак
    0.34
     vocab
    0.34
     रिएक्ट
    0.34
    🅔
    0.34
    の実
    0.33
     Parameters
    0.33
     পাঠক
    0.33
    }^{+},
    0.33
    Activations Density 0.001%

    No Known Activations