© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204927
    Prev
    Next
    INDEX
    Explanations

    writing style

    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_46_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
     अग्
    0.40
    ovu
    0.39
    <?=
    0.39
     leftist
    0.37
    amente
    0.36
     آهنگ
    0.36
     கா
    0.36
     հ
    0.35
    Because
    0.34
    வ்வாறு
    0.34
    POSITIVE LOGITS
    िकल
    0.42
    टल
    0.37
     đột
    0.37
    idon
    0.37
     fusible
    0.36
     IDC
    0.35
     remer
    0.35
    licher
    0.35
     paise
    0.35
    मेस्टर
    0.34
    Activations Density 0.001%

    No Known Activations