© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43396
    Prev
    Next
    INDEX
    Explanations

    precious

    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_3_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
    ne
    0.89
    s
    0.86
    t
    0.74
    sing
    0.72
    ating
    0.70
    ments
    0.70
    いた
    0.69
    ng
    0.67
    ances
    0.66
    likely
    0.66
    POSITIVE LOGITS
    ור
    0.73
     darf
    0.73
    ാ
    0.71
    ول
    0.71
     skoro
    0.69
    ü
    0.69
     této
    0.68
     soll
    0.66
     spoloč
    0.66
    р
    0.66
    Activations Density 0.000%

    No Known Activations