© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15296
    Prev
    Next
    INDEX
    Explanations

    claims and theories

    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_34_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
    કારો
    0.39
    ASSI
    0.38
    ૃત
    0.37
     espè
    0.37
     #####
    0.37
     знали
    0.37
    Assured
    0.37
     desenho
    0.36
    ैसे
    0.36
    ₎
    0.36
    POSITIVE LOGITS
     kul
    0.43
     modular
    0.41
     rampant
    0.39
    kul
    0.38
     Exp
    0.37
     Kü
    0.37
     Ions
    0.36
     Re
    0.36
     HC
    0.36
     Modular
    0.36
    Activations Density 0.201%

    No Known Activations