© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135131
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     REL
    0.42
     CPUs
    0.36
    ಣ
    0.36
     cpu
    0.35
    ACLE
    0.35
     CPU
    0.34
     カー
    0.34
     PCM
    0.33
     PSL
    0.33
    氣
    0.33
    POSITIVE LOGITS
    ukannya
    0.43
     पो
    0.41
    ம்ப
    0.40
    daction
    0.39
     opened
    0.39
     सन्
    0.38
    ᱮ
    0.38
    contre
    0.38
    वेश
    0.38
     phosphor
    0.38
    Activations Density 0.000%

    No Known Activations