© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80100
    Prev
    Next
    INDEX
    Explanations

    polarization

    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_0_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
    t
    1.72
    of
    1.63
    ties
    1.51
    ted
    1.30
    tan
    1.30
    tr
    1.30
    top
    1.29
    c
    1.26
    ျေး
    1.24
    tion
    1.23
    POSITIVE LOGITS
    ↵↵
    1.79
    ,
    1.63
    ↵
    1.48
    4
    1.45
    ру
    1.43
    5
    1.39
    с
    1.32
    没有
    1.24
     can
    1.23
     e
    1.20
    Activations Density 0.001%

    No Known Activations