© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97845
    Prev
    Next
    INDEX
    Explanations

    Eurozone

    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_14_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
    𖥔
    0.58
    ches
    0.58
    nilvadipine
    0.57
     Greenfield
    0.55
    Baseball
    0.54
    nati
    0.54
    λης
    0.53
     Forma
    0.50
    ijnlijk
    0.50
    ar
    0.50
    POSITIVE LOGITS
     secretion
    0.52
     possíveis
    0.52
     concatenation
    0.52
     joué
    0.51
     stripes
    0.50
    전
    0.49
    ляются
    0.48
    ن
    0.48
     contenu
    0.48
     столько
    0.47
    Activations Density 0.001%

    No Known Activations