© 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. 124003
    Prev
    Next
    INDEX
    Explanations

    Russian and Chinese words

    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
    to
    0.66
    ле
    0.66
    一
    0.66
    the
    0.63
    </h1>
    0.63
    р
    0.63
    ----------------
    0.62
    ت
    0.62
    us
    0.62
    t
    0.62
    POSITIVE LOGITS
    𝓭
    0.75
    𝒉
    0.71
    Mp
    0.68
     it
    0.66
     énergétique
    0.66
    Mu
    0.64
    ㏄
    0.63
    \}.
    0.62
    𝓶
    0.62
    𝔪
    0.62
    Activations Density 0.000%

    No Known Activations