© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13685
    Prev
    Next
    INDEX
    Explanations

    sequences of ones and mathematical operators

    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_13_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
    ul
    0.42
    de
    0.42
    ::
    0.39
    id
    0.38
     from
    0.36
     d
    0.35
    from
    0.35
    ir
    0.35
    SP
    0.35
    illar
    0.34
    POSITIVE LOGITS
     ।”
    0.35
    ।”
    0.34
    akarta
    0.33
     ?”
    0.33
    ورٹی
    0.32
     Août
    0.31
    ’.”
    0.31
    똘
    0.31
    <unused50>
    0.30
    ρία
    0.30
    Activations Density 0.011%

    No Known Activations