© 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. 201233
    Prev
    Next
    INDEX
    Explanations

    cost to

    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
    é
    1.25
    ী
    1.12
    ش
    1.08
    ij
    1.02
    the
    1.01
     ένα
    1.01
    ü
    1.00
    by
    0.98
    way
    0.95
     OFW
    0.94
    POSITIVE LOGITS
    。
    1.33
    ।
    0.85
     diretor
    0.84
    高志森
    0.84
    s
    0.83
    ал
    0.82
     collaborator
    0.82
     Melhor
    0.82
     funkce
    0.80
    ે
    0.79
    Activations Density 0.002%

    No Known Activations