© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60880
    Prev
    Next
    INDEX
    Explanations

    exact same

    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_2_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
    ل
    1.21
    kWh
    1.01
    same
    0.93
    am
    0.88
     gleiche
    0.88
    твори
    0.85
    好吃
    0.83
    филлер
    0.82
    that
    0.82
    phalodes
    0.82
    POSITIVE LOGITS
    ،
    1.26
    اک
    1.17
    в
    1.09
    ला
    1.08
    ש
    1.07
    ၊
    1.04
    ير
    1.02
    <0x91>
    0.98
    <0x98>
    0.95
    ，
    0.94
    Activations Density 0.000%

    No Known Activations