© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80717
    Prev
    Next
    INDEX
    Explanations

    braided hair descriptions

    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_0_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
     powied
    1.58
    </strong>
    1.43
    -
    1.31
    at
    1.30
     сообщи
    1.27
     заяви
    1.27
    </h2>
    1.26
    </h3>
    1.26
    ни
    1.25
     않았
    1.22
    POSITIVE LOGITS
    f
    1.90
    s
    1.76
    t
    1.52
    typen
    1.41
    вати
    1.27
     in
    1.18
    ের
    1.16
    tt
    1.16
    d
    1.16
    től
    1.15
    Activations Density 0.000%

    No Known Activations