© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136520
    Prev
    Next
    INDEX
    Explanations

    Award Winners, blogger named, Storage

    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_12_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
     Are
    0.54
     flavor
    0.53
    ve
    0.51
    ter
    0.51
    븐
    0.48
    mas
    0.48
    aka
    0.48
     (
    0.48
     Argu
    0.48
    Ah
    0.47
    POSITIVE LOGITS
     clip
    0.52
     jacuzzi
    0.52
     استاذ
    0.52
     జరిగిన
    0.52
    జేపీ
    0.50
     Bauhaus
    0.49
    =-\
    0.49
    страницу
    0.49
    довж
    0.48
    သေး
    0.48
    Activations Density 0.004%

    No Known Activations