© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126358
    Prev
    Next
    INDEX
    Explanations

    openai api

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    깐
    0.79
    ゅう
    0.64
    ņš
    0.63
    ệu
    0.55
    ょう
    0.54
    ږي
    0.54
    yah
    0.54
    ège
    0.53
    য়া
    0.52
    یە
    0.52
    POSITIVE LOGITS
    నూ
    0.49
    ो
    0.45
    ai
    0.44
    ను
    0.43
    all
    0.43
    ייה
    0.42
    eb
    0.41
    ione
    0.41
    anía
    0.41
    ો
    0.41
    Activations Density 0.008%

    No Known Activations