© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51432
    Prev
    Next
    INDEX
    Explanations

    j

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    拷贝
    0.42
    ر
    0.36
     Saheb
    0.35
     (…)
    0.35
     trem
    0.34
     `<`,
    0.34
     dirs
    0.34
     Observations
    0.34
     Copy
    0.34
     Geometry
    0.33
    POSITIVE LOGITS
    ्ञ
    0.46
    咟
    0.43
    ekt
    0.42
    assadors
    0.40
    ésus
    0.40
    útbol
    0.40
    tu
    0.40
    lesh
    0.39
    essor
    0.39
     скло
    0.39
    Activations Density 0.002%

    No Known Activations