© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213797
    Prev
    Next
    INDEX
    Explanations

    software

    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_50_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
    NESS
    0.50
    ness
    0.49
    rip
    0.43
    NotExist
    0.42
    liv
    0.42
    rada
    0.41
    ぅ
    0.40
    did
    0.39
    ье
    0.39
    ДИ
    0.39
    POSITIVE LOGITS
    xt
    0.54
    ğin
    0.48
    holder
    0.48
    iramente
    0.48
    cko
    0.47
    cki
    0.46
    ٔ
    0.46
    ́
    0.46
    ffected
    0.46
    legant
    0.45
    Activations Density 0.011%

    No Known Activations