© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138111
    Prev
    Next
    INDEX
    Explanations

    caliber, cartridge, mm

    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_12_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
    pack
    0.32
    ansion
    0.32
    Info
    0.31
    Ч
    0.31
    info
    0.31
    br
    0.30
    It
    0.30
    ^+
    0.30
    I
    0.30
    ljiv
    0.30
    POSITIVE LOGITS
     cursing
    0.34
     frantically
    0.33
     cí
    0.32
    cí
    0.32
     uncon
    0.31
    ى
    0.31
     heroine
    0.30
     agony
    0.30
     nhiên
    0.29
     frantic
    0.29
    Activations Density 0.000%

    No Known Activations