© 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. 107937
    Prev
    Next
    INDEX
    Explanations

    travelling to places

    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
    S
    0.86
    O
    0.79
    婪
    0.77
    SearchCV
    0.76
    دى
    0.75
    M
    0.75
    东西
    0.74
    用
    0.74
    MIDI
    0.73
    ELL
    0.73
    POSITIVE LOGITS
    '
    1.20
    (
    1.05
    که
    1.03
    ओं
    0.98
    i
    0.87
    ali
    0.85
    ani
    0.82
    να
    0.81
    the
    0.80
    ka
    0.80
    Activations Density 0.000%

    No Known Activations