© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133759
    Prev
    Next
    INDEX
    Explanations

    forts

    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_1_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
    t
    1.32
    i
    1.30
    a
    1.23
    d
    1.15
    e
    1.09
    m
    1.08
    RA
    1.01
    n
    1.01
     Model
    1.00
    dS
    0.96
    POSITIVE LOGITS
    al
    1.18
    ного
    1.00
    aneous
    0.96
    .
    0.95
    بی
    0.88
    ating
    0.87
    kol
    0.85
    ль
    0.82
    ld
    0.79
    leg
    0.78
    Activations Density 0.000%

    No Known Activations