© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51907
    Prev
    Next
    INDEX
    Explanations

    operating profit/margin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    тельной
    0.41
    ற்க
    0.40
    ither
    0.38
    tel
    0.38
    決勝
    0.38
    тельные
    0.37
     Blond
    0.37
    匆
    0.37
     embodiments
    0.36
     demands
    0.36
    POSITIVE LOGITS
     jumpers
    0.39
     shocks
    0.38
     Selling
    0.38
    ciation
    0.37
    करणा
    0.37
     கரைய
    0.36
     jumps
    0.35
    StartsWith
    0.35
    startswith
    0.34
     climbs
    0.34
    Activations Density 0.005%

    No Known Activations