© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63527
    Prev
    Next
    INDEX
    Explanations

    Raven or Ravenna

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    濁
    0.42
     Alo
    0.39
    Sung
    0.38
    వై
    0.38
     Sung
    0.38
    ტურ
    0.38
    浊
    0.38
    寨
    0.38
    Alo
    0.37
     Akan
    0.37
    POSITIVE LOGITS
    Raven
    1.18
     Ravenna
    1.11
     raven
    1.02
     Raven
    1.02
     RAV
    0.89
    raven
    0.80
     Rav
    0.79
     Ravens
    0.78
     Bologna
    0.78
    Rav
    0.77
    Activations Density 0.010%

    No Known Activations