© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166311
    Prev
    Next
    INDEX
    Explanations

    video content creation

    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_31_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
     निर्म
    0.37
    嘆
    0.36
     Certificate
    0.36
     animated
    0.35
     technician
    0.35
     worker
    0.35
     suminist
    0.35
     buoni
    0.34
    停止
    0.34
    agn
    0.33
    POSITIVE LOGITS
     pena
    0.37
    ᾧ
    0.37
     dedicar
    0.36
     Moff
    0.36
     हृदया
    0.36
    норийска
    0.35
    Waste
    0.35
     अराउंड
    0.35
    グラム
    0.35
    タク
    0.34
    Activations Density 0.001%

    No Known Activations