© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53586
    Prev
    Next
    INDEX
    Explanations

    isolated and purified

    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_30_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
     теорети
    0.38
    咲
    0.37
     Names
    0.36
    検証
    0.36
    }+\
    0.36
     Colleg
    0.36
     Colonial
    0.36
     बाध्य
    0.35
     कॉले
    0.35
    理论
    0.34
    POSITIVE LOGITS
    ensions
    0.37
    弦
    0.36
    opolis
    0.36
     purified
    0.35
    tension
    0.35
     halde
    0.35
     frequencies
    0.35
    FIT
    0.35
    FREQ
    0.35
     tensions
    0.34
    Activations Density 0.001%

    No Known Activations