© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137363
    Prev
    Next
    INDEX
    Explanations

    season records and rankings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     ser
    0.49
    級
    0.42
     forgo
    0.38
    abeth
    0.38
     tough
    0.37
     thyme
    0.37
     Abandon
    0.37
    abbo
    0.37
     ਜਾ
    0.36
    utable
    0.36
    POSITIVE LOGITS
     idxf
    0.37
    0.37
     scores
    0.37
     gains
    0.37
     bandes
    0.36
     неот
    0.35
    (<
    0.35
    weekly
    0.35
    ண்டி
    0.35
     ψ
    0.34
    Activations Density 0.000%

    No Known Activations