© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66392
    Prev
    Next
    INDEX
    Explanations

    say X

    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_51_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
    sas
    0.47
    ans
    0.43
    lub
    0.43
    सान
    0.42
    واه
    0.42
    사
    0.42
    ureshi
    0.41
    unto
    0.41
    ansı
    0.40
    kas
    0.40
    POSITIVE LOGITS
    ത്തെ
    0.43
     шу
    0.39
     ಕಳೆದ
    0.37
    鸦
    0.37
     awak
    0.36
    耖
    0.36
    缘
    0.35
     shouts
    0.35
    োদিত
    0.35
     കഴിഞ്ഞ
    0.35
    Activations Density 0.004%

    No Known Activations