© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44616
    Prev
    Next
    INDEX
    Explanations

    printables, demand

    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_3_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
     inhomogeneities
    0.71
     celular
    0.64
     său
    0.63
    ט
    0.63
     edema
    0.61
    는데
    0.61
     malignancies
    0.61
     소녀
    0.61
    </sub>
    0.60
     شکل
    0.60
    POSITIVE LOGITS
    in
    1.10
    s
    1.04
    as
    0.87
    at
    0.79
    ie
    0.78
    و
    0.77
    h
    0.74
    ren
    0.73
    ia
    0.73
    en
    0.71
    Activations Density 0.014%

    No Known Activations