© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145681
    Prev
    Next
    INDEX
    Explanations

    political discussions

    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
     on
    1.71
    К
    1.59
    ни
    1.55
    на
    1.46
    ٢
    1.38
    2
    1.37
    on
    1.34
     fraudulently
    1.26
     ﺍ
    1.23
    kiej
    1.23
    POSITIVE LOGITS
    지
    1.51
    n
    1.50
     as
    1.48
    కు
    1.48
    l
    1.45
    ii
    1.40
    도
    1.38
    an
    1.37
    the
    1.27
    는
    1.27
    Activations Density 0.000%

    No Known Activations