© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50948
    Prev
    Next
    INDEX
    Explanations

    display alert messages

    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_31_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
    镇
    0.47
     passeio
    0.41
     galactose
    0.40
     personalidade
    0.39
     reconocimiento
    0.39
    ография
    0.39
     coscienza
    0.39
    infodisc
    0.39
     病
    0.38
    ighe
    0.38
    POSITIVE LOGITS
     torn
    0.45
     cursed
    0.41
     Torn
    0.40
     successor
    0.39
     tore
    0.39
    torn
    0.39
     Curtis
    0.38
     Vorder
    0.38
     GR
    0.38
     Mehr
    0.38
    Activations Density 0.006%

    No Known Activations