© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49450
    Prev
    Next
    INDEX
    Explanations

    say verbs

    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
    тріш
    0.40
     Mato
    0.38
    гій
    0.36
    增
    0.36
    ">-->
    0.35
     कैलेंडर
    0.35
    筛选
    0.35
    VCT
    0.34
    曆
    0.34
    睁
    0.34
    POSITIVE LOGITS
    performs
    0.44
     outperforms
    0.44
     performed
    0.43
     परफॉर्म
    0.42
     declines
    0.42
     outperform
    0.42
     performers
    0.41
    performed
    0.40
    iquette
    0.40
     outperformed
    0.40
    Activations Density 0.001%

    No Known Activations