© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121292
    Prev
    Next
    INDEX
    Explanations

    To [action verb]

    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_27_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
     uma
    0.42
     efforts
    0.42
     subjective
    0.39
     investigations
    0.38
     저
    0.38
     a
    0.38
     commentary
    0.37
    重複
    0.37
     CRP
    0.37
     planning
    0.37
    POSITIVE LOGITS
    Przyp
    0.45
     ጥቅም
    0.39
    Deutschland
    0.38
    রত্ব
    0.37
    டக்கலை
    0.37
    Television
    0.36
    ($("#
    0.36
     งวด
    0.36
     Preset
    0.36
    odeal
    0.35
    Activations Density 0.002%

    No Known Activations