© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107827
    Prev
    Next
    INDEX
    Explanations

    subtle distinctions

    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_1_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
    ons
    1.10
    ien
    1.09
    و
    1.07
    ode
    1.05
    ied
    0.98
    ian
    0.98
    ו
    0.96
    aping
    0.96
    out
    0.95
    ry
    0.92
    POSITIVE LOGITS
    是
    1.31
    تي
    1.29
    سي
    1.16
    는
    1.13
    ።
    1.12
    .
    1.11
    ר
    1.10
    は
    1.08
    ۔
    1.07
    ม
    1.06
    Activations Density 0.005%

    No Known Activations