© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 710
    Prev
    Next
    INDEX
    Explanations

    code examples with output

    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_40_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
     u
    0.73
     U
    0.52
     उ
    0.52
     ‘
    0.43
     ع
    0.42
     Ulysses
    0.41
    list
    0.41
    U
    0.41
     う
    0.40
    u
    0.40
    POSITIVE LOGITS
    osphäre
    0.36
     restarted
    0.35
     poč
    0.35
    يرين
    0.34
    quiries
    0.34
     rangers
    0.33
     footer
    0.33
    @@]
    0.33
    ishable
    0.33
    权威
    0.33
    Activations Density 0.013%

    No Known Activations