© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206614
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ć
    0.46
    iejs
    0.45
     hígado
    0.45
     lokalen
    0.44
    حي
    0.43
     tradicionales
    0.43
    hā
    0.43
    abies
    0.43
    низу
    0.42
    ステン
    0.42
    POSITIVE LOGITS
     backlash
    0.44
     चन्द्र
    0.44
     fellow
    0.42
    =@
    0.42
    parency
    0.41
     cautiously
    0.40
     whips
    0.40
     CTA
    0.40
     defaulting
    0.40
     its
    0.40
    Activations Density 0.000%

    No Known Activations