© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163635
    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_13_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
    ות
    0.53
    ResponseBody
    0.49
     indoss
    0.48
    רת
    0.48
    উ
    0.47
     στον
    0.47
    DCTask
    0.47
    StartZ
    0.46
    వ
    0.46
    ر
    0.46
    POSITIVE LOGITS
    ly
    0.48
    ny
    0.45
    ម្ល
    0.43
    igh
    0.43
    сное
    0.42
    ăn
    0.41
     coercive
    0.41
     चालीस
    0.41
    uj
    0.40
     Valuable
    0.40
    Activations Density 0.000%

    No Known Activations