© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40412
    Prev
    Next
    INDEX
    Explanations

    symbolic representations

    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_11_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
    اتها
    0.29
     enige
    0.28
    崛起
    0.28
    ка
    0.27
    </h1>
    0.27
     umožňuje
    0.26
     ejecut
    0.26
     Mhm
    0.25
    </h4>
    0.25
    </sub>
    0.25
    POSITIVE LOGITS
    to
    0.37
    deformation
    0.33
    requirement
    0.32
    displacement
    0.31
    carbon
    0.31
    trans
    0.30
    xs
    0.30
    Fer
    0.29
    coes
    0.29
    mineral
    0.29
    Activations Density 0.019%

    No Known Activations