© 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. 167678
    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_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
     VT
    0.44
     allocates
    0.36
     sired
    0.36
    벳
    0.36
    लाइज
    0.35
     Figaro
    0.34
     benzene
    0.34
     manages
    0.34
     Vt
    0.33
    ोजना
    0.33
    POSITIVE LOGITS
    Sch
    0.45
    jsce
    0.40
    电
    0.39
     Schol
    0.38
     सोम
    0.38
    ose
    0.37
    età
    0.37
    ješ
    0.36
    élect
    0.36
    齐
    0.36
    Activations Density 0.000%

    No Known Activations