© 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. 133905
    Prev
    Next
    INDEX
    Explanations

    core part 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_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
    </h3>
    1.02
    Tôi
    0.87
    ột
    0.86
    ias
    0.85
    '
    0.84
    0.84
    artige
    0.83
                 
    0.83
    ᱐
    0.82
    \
    0.81
    POSITIVE LOGITS
    g
    1.32
    v
    1.23
    t
    1.20
    p
    1.11
    נ
    1.11
    c
    1.01
    m
    1.01
    ্স
    0.98
    s
    0.98
    ENTY
    0.96
    Activations Density 0.015%

    No Known Activations