© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158513
    Prev
    Next
    INDEX
    Explanations

    bracketed phrases

    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_2_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
    ча
    1.32
    로
    1.20
    и
    1.19
    ية
    1.13
    ле
    1.11
    נו
    1.09
    і
    1.09
    ся
    1.06
    у
    1.06
    으로
    1.01
    POSITIVE LOGITS
    ↵↵
    1.57
    tim
    1.19
    ו
    1.16
    ta
    1.08
    ar
    1.02
    <h2>
    1.01
    ica
    1.00
    til
    0.98
    tit
    0.98
    A
    0.96
    Activations Density 0.000%

    No Known Activations