© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231787
    Prev
    Next
    INDEX
    Explanations

    familial relationships and conditions

    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_6_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
    1
    1.15
     pessoais
    0.97
    ।
    0.96
     allemand
    0.96
     exteriores
    0.95
    It
    0.94
    आर
    0.93
    ל
    0.93
     hypersurfaces
    0.91
     can
    0.89
    POSITIVE LOGITS
    i
    1.10
    in
    1.09
    f
    0.96
    y
    0.93
    "
    0.84
    ta
    0.80
    い
    0.78
    l
    0.77
    st
    0.76
    ð
    0.75
    Activations Density 0.000%

    No Known Activations