© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28332
    Prev
    Next
    INDEX
    Explanations

    Korean stories or explanations

    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
     exclusives
    0.39
    álise
    0.38
    '`--
    0.38
     विनाश
    0.37
     সহ
    0.36
     nField
    0.36
    䧺
    0.36
     ساز
    0.35
    जिए
    0.35
    nici
    0.35
    POSITIVE LOGITS
     Hearts
    0.42
     hearts
    0.41
     மூன்ற
    0.39
     reputation
    0.39
    胎
    0.39
    Hearts
    0.38
     fmt
    0.37
     Reputation
    0.37
    Pub
    0.37
     Heart
    0.36
    Activations Density 0.021%

    No Known Activations