© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33166
    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
    फा
    0.37
     faculty
    0.37
    を楽しむ
    0.36
    ..--
    0.36
    കാ
    0.35
    Dick
    0.35
    Sing
    0.35
     celebrating
    0.34
    jest
    0.34
    يني
    0.34
    POSITIVE LOGITS
     sorption
    0.40
     inspected
    0.39
    }^{+}=
    0.38
    槨
    0.38
    اوم
    0.37
    ామ
    0.36
    лып
    0.36
     цу
    0.36
     structuring
    0.36
     AID
    0.36
    Activations Density 0.000%

    No Known Activations