© 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. 108152
    Prev
    Next
    INDEX
    Explanations

    Pro followed by specific suffixes

    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
     characterise
    1.18
     pudiera
    1.05
    ۰
    1.05
     juries
    1.02
    AS
    1.02
     characterize
    1.01
    INE
    1.00
    UT
    0.99
     fuselage
    0.98
     motos
    0.98
    POSITIVE LOGITS
    的
    0.99
    其
    0.98
    지만
    0.98
    S
    0.98
    an
    0.95
    kval
    0.93
    ని
    0.89
    ৬
    0.88
    ai
    0.87
    ier
    0.86
    Activations Density 0.001%

    No Known Activations