© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    ffmpeg crop syntax

    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
    綎
    0.40
     dialogues
    0.40
     Fool
    0.39
     messes
    0.39
     cias
    0.37
     bootstrapping
    0.37
     Document
    0.37
     exce
    0.36
     motions
    0.35
    elize
    0.35
    POSITIVE LOGITS
    TeV
    0.40
    铛
    0.40
    brev
    0.37
    უკ
    0.36
     pä
    0.35
     bestät
    0.35
     threatened
    0.35
    }=\{\
    0.35
     testAvg
    0.35
    Threat
    0.34
    Activations Density 0.009%

    No Known Activations