© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    ripple effect snowball domino

    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
     proz
    0.41
     Proz
    0.40
     chromat
    0.39
    铬
    0.39
    hegan
    0.38
     Zac
    0.38
    鉻
    0.38
     Chromebook
    0.37
    andad
    0.37
     Hugh
    0.37
    POSITIVE LOGITS
     snowball
    2.13
    snow
    1.65
    Snow
    1.61
     snow
    1.59
     Snow
    1.58
    雪
    1.56
     domino
    1.52
     сне
    1.31
     ripple
    1.30
     雪
    1.30
    Activations Density 0.278%

    No Known Activations