© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147730
    Prev
    Next
    INDEX
    Explanations

    gear shift lever

    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_18_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
    ুব
    0.46
    ⚙
    0.46
    ﾓ
    0.44
    ൩
    0.43
    ellung
    0.43
    䡃
    0.41
    년에
    0.41
    필
    0.40
    𝗍
    0.40
     Versorgung
    0.40
    POSITIVE LOGITS
     sweetener
    0.52
     drinks
    0.50
     beverage
    0.49
     beverages
    0.47
     kindergarten
    0.47
     paparazzi
    0.47
     drink
    0.47
     hims
    0.47
     sweetest
    0.46
    ua
    0.46
    Activations Density 0.000%

    No Known Activations