© 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. 243278
    Prev
    Next
    INDEX
    Explanations

    before buying

    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
    rib
    0.41
    Et
    0.40
    ([])
    0.39
    rgb
    0.37
     sometimes
    0.36
    avip
    0.35
    atka
    0.34
     invasive
    0.34
    有时
    0.34
     ethical
    0.34
    POSITIVE LOGITS
    Connectivity
    0.42
     суме
    0.41
     Connectivity
    0.40
    暠
    0.40
    সৌ
    0.40
    moja
    0.39
     dokon
    0.39
     Connelly
    0.39
    上げた
    0.39
    гово
    0.38
    Activations Density 0.004%

    No Known Activations