© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131874
    Prev
    Next
    INDEX
    Explanations

    best interest

    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
    '
    1.02
     for
    0.92
     islets
    0.83
     heirs
    0.82
     connaissances
    0.81
     automorphisms
    0.81
     failings
    0.81
     redshifts
    0.80
     cliffs
    0.80
     conseils
    0.80
    POSITIVE LOGITS
    g
    1.61
    q
    1.33
    Y
    1.23
    t
    1.21
    p
    1.11
    e
    1.02
    al
    1.02
    c
    1.02
    AN
    1.01
    y
    1.00
    Activations Density 0.000%

    No Known Activations