© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69450
    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_51_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
     যশোর
    0.43
     banquet
    0.42
     Banquet
    0.42
     Riot
    0.40
    ޢ
    0.38
    鷄
    0.38
    jab
    0.38
     outlaw
    0.38
     ગો
    0.37
    Moj
    0.37
    POSITIVE LOGITS
    fol
    0.42
    8
    0.39
     fol
    0.39
    扮
    0.37
     Fol
    0.36
     §
    0.36
    ophone
    0.35
    intensity
    0.35
     Sammy
    0.35
     folgte
    0.34
    Activations Density 0.000%

    No Known Activations