© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31279
    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_40_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
    دید
    0.41
    OSED
    0.41
    ELINE
    0.40
    單
    0.39
     single
    0.38
    Ἠ
    0.38
    空的
    0.37
     nest
    0.36
     单
    0.36
    Ę
    0.36
    POSITIVE LOGITS
    Keep
    0.37
    Back
    0.35
     Kall
    0.34
    Case
    0.34
    Kn
    0.34
    Approach
    0.34
     Pap
    0.33
    Swap
    0.33
    Replace
    0.32
     கற்க
    0.32
    Activations Density 0.000%

    No Known Activations