© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33725
    Prev
    Next
    INDEX
    Explanations

    Peninsula

    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_3_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
    "
    0.81
    '
    0.70
    );
    0.66
    asjonen
    0.63
    anfaatkan
    0.61
     불구하고
    0.61
    રણ
    0.60
    t
    0.60
    নি
    0.59
    กล่าว
    0.59
    POSITIVE LOGITS
     года
    0.64
    к
    0.61
    imony
    0.61
    ی
    0.60
    ﺑ
    0.60
    𝒊
    0.60
    velocity
    0.58
     Ди
    0.57
    ﺗ
    0.57
    problem
    0.57
    Activations Density 0.000%

    No Known Activations