© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45472
    Prev
    Next
    INDEX
    Explanations

    form properties and extensions

    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_13_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
    en
    0.53
     la
    0.48
     husband
    0.47
     submit
    0.46
     planks
    0.46
     eup
    0.46
     slay
    0.44
     \
    0.43
     action
    0.43
    知
    0.42
    POSITIVE LOGITS
     Verhältnis
    0.59
     forêts
    0.57
     Tsch
    0.57
     약
    0.55
     Wä
    0.55
    𝟭
    0.55
     तंत्र
    0.54
     தேர்வு
    0.54
    쇤
    0.54
     Bildschirm
    0.54
    Activations Density 0.001%

    No Known Activations