© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88923
    Prev
    Next
    INDEX
    Explanations

    festivals and ales

    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_23_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
    ognito
    0.43
    ✅
    0.42
    webhook
    0.41
     nft
    0.39
    JWT
    0.39
    Rainbow
    0.39
     ይሆ
    0.39
     Quotient
    0.38
    Metric
    0.37
    bookmark
    0.37
    POSITIVE LOGITS
     examine
    0.46
     Examine
    0.42
    @[+][
    0.39
     laser
    0.38
     examined
    0.38
     frei
    0.38
     JAMA
    0.38
     TIP
    0.37
     அளவு
    0.36
     kunde
    0.36
    Activations Density 0.002%

    No Known Activations