© 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. 985
    Prev
    Next
    INDEX
    Explanations

    survival and actions

    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
    hasClass
    0.36
     දැන
    0.36
     اسئله
    0.35
     vén
    0.35
     Balt
    0.35
     errorMessage
    0.35
    يلة
    0.34
    욤
    0.34
     سبک
    0.34
    avasti
    0.34
    POSITIVE LOGITS
     survives
    0.38
     Critique
    0.35
     Launch
    0.34
    کری
    0.34
     Gas
    0.32
     survive
    0.32
     survived
    0.32
    දේශ
    0.32
     stressed
    0.31
     Bonif
    0.31
    Activations Density 0.059%

    No Known Activations