© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145296
    Prev
    Next
    INDEX
    Explanations

    cost-effectiveness

    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_0_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
    ки
    1.92
    ის
    1.63
    ся
    1.36
    ası
    1.32
    é
    1.30
    1.29
    ни
    1.26
    و
    1.26
     և
    1.25
    .
    1.24
    POSITIVE LOGITS
    i
    1.72
    0
    1.70
    Z
    1.52
    ти
    1.44
    D
    1.41
    #
    1.40
    DD
    1.36
    Q
    1.31
    O
    1.30
    ૦
    1.26
    Activations Density 0.001%

    No Known Activations