© 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. 57550
    Prev
    Next
    INDEX
    Explanations

    stove

    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
    ক্স
    0.62
    嚧
    0.60
    hours
    0.59
     用于
    0.59
    bär
    0.57
    žky
    0.57
    tis
    0.57
    ləşdir
    0.57
     Grüße
    0.57
    anders
    0.56
    POSITIVE LOGITS
     innovation
    0.58
    </i>
    0.56
    </h6>
    0.55
     concetto
    0.53
    </em>
    0.53
     cu
    0.52
     dichotomy
    0.52
     genetic
    0.51
    s
    0.50
    </h3>
    0.50
    Activations Density 0.002%

    No Known Activations