© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215447
    Prev
    Next
    INDEX
    Explanations

    please consult a professional

    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_31_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
     contextual
    0.45
    ALI
    0.41
    茆
    0.40
    Trial
    0.39
     trial
    0.37
     Geoffrey
    0.37
     tightened
    0.37
     Trial
    0.36
     core
    0.36
    特定的
    0.36
    POSITIVE LOGITS
     elegance
    0.42
     ఇక
    0.39
    ර්
    0.38
     acudir
    0.38
    scss
    0.36
     simplemente
    0.36
    ẏ
    0.36
     popul
    0.35
     hãy
    0.34
    豪華
    0.34
    Activations Density 0.002%

    No Known Activations