© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194583
    Prev
    Next
    INDEX
    Explanations

    floods and related events

    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_15_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
    𝙸
    0.44
    РА
    0.43
     ~/.
    0.43
     ".$
    0.42
     إس
    0.41
     jedynie
    0.39
    𝕕
    0.39
     поги
    0.39
    。</
    0.39
     Роман
    0.38
    POSITIVE LOGITS
    ches
    0.36
    ession
    0.36
    turquoise
    0.36
    sel
    0.35
    bq
    0.34
    oqu
    0.33
    blueberry
    0.32
     Finland
    0.32
    pron
    0.31
    el
    0.31
    Activations Density 0.002%

    No Known Activations