© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156582
    Prev
    Next
    INDEX
    Explanations

    lots of

    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_2_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
     cuales
    0.85
     の
    0.84
     ='
    0.83
     ganh
    0.82
     clarinet
    0.82
     magia
    0.81
     memoria
    0.80
    דה
    0.80
     previsto
    0.80
     paradig
    0.80
    POSITIVE LOGITS
    on
    1.56
    ut
    1.56
    to
    1.53
    us
    1.49
    at
    1.39
    m
    1.32
    s
    1.30
    um
    1.27
    ю
    1.26
    ur
    1.25
    Activations Density 0.001%

    No Known Activations