© 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. 146036
    Prev
    Next
    INDEX
    Explanations

    wh followed by various punctuation/special characters

    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
    te
    1.74
    u
    1.62
    v
    1.53
    f
    1.46
    er
    1.43
    ty
    1.42
    et
    1.41
    r
    1.34
    ai
    1.23
    ts
    1.22
    POSITIVE LOGITS
    ۔
    1.52
    ス
    1.44
    は
    1.39
    (
    1.38
    는
    1.33
    एस
    1.32
    เป็น
    1.32
    な
    1.32
    </sup>
    1.31
    的
    1.28
    Activations Density 0.001%

    No Known Activations