© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216385
    Prev
    Next
    INDEX
    Explanations

    Visa types, registers, writing systems

    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_31_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
     Petter
    0.36
    maxLength
    0.35
     Reno
    0.34
     বেন
    0.33
    鬃
    0.33
    孙
    0.33
     おり
    0.32
    ⺊
    0.32
     Renato
    0.32
    ალაქ
    0.31
    POSITIVE LOGITS
     discriminating
    0.42
    ස්ථ
    0.36
    imposed
    0.35
     bumi
    0.33
    வங்க
    0.33
     Pharmacy
    0.33
    doll
    0.33
    jach
    0.33
     discrim
    0.33
     superimposed
    0.32
    Activations Density 0.000%

    No Known Activations