© 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. 127675
    Prev
    Next
    INDEX
    Explanations

    tower, garden, mountain, dragon, dancer

    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
    ined
    0.70
    ated
    0.67
    (
    0.66
    ان
    0.64
    aim
    0.64
    anging
    0.64
    ate
    0.63
    ape
    0.62
    ador
    0.62
    ingale
    0.61
    POSITIVE LOGITS
    傆
    0.62
    ta
    0.61
    이었다
    0.58
    শকা
    0.57
    ದ್ದರಿಂದ
    0.57
    喡
    0.56
    ں
    0.55
    大海
    0.55
     Ș
    0.54
    urilor
    0.54
    Activations Density 0.001%

    No Known Activations