© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2821
    Prev
    Next
    INDEX
    Explanations

    casting shadows

    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_40_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
    erapeut
    0.39
    鸥
    0.38
    जोन
    0.37
    endorf
    0.37
    ">/</
    0.37
     disappears
    0.36
     আর্কাইভ
    0.36
    clang
    0.36
    消失
    0.35
    遺
    0.35
    POSITIVE LOGITS
     elongated
    0.46
     stretching
    0.43
     dropping
    0.41
     twisting
    0.41
     dreaming
    0.41
     painting
    0.40
     distort
    0.39
     bleeding
    0.39
     растя
    0.38
     drop
    0.38
    Activations Density 0.296%

    No Known Activations