© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53245
    Prev
    Next
    INDEX
    Explanations

    java imports and annotations

    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_30_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
    ENERGY
    0.39
    治
    0.38
    Hood
    0.37
    Phys
    0.37
    Chel
    0.37
    Correo
    0.36
    Theoretical
    0.35
    ㄜ
    0.35
    Hop
    0.34
     regiones
    0.34
    POSITIVE LOGITS
    aintiff
    0.35
     komm
    0.35
     twentieth
    0.35
     Palm
    0.35
     നിര
    0.35
     fr
    0.34
     palm
    0.34
     '['
    0.34
     Rather
    0.33
    രിയ
    0.33
    Activations Density 0.000%

    No Known Activations