© 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. 82262
    Prev
    Next
    INDEX
    Explanations

    OTHER

    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
    t
    3.34
    től
    1.41
    tä
    1.35
    tR
    1.34
    k
    1.30
    ות
    1.27
    ت
    1.25
    ย
    1.25
    А
    1.24
    taker
    1.23
    POSITIVE LOGITS
    ير
    1.45
     огромное
    1.44
    ور
    1.38
     científ
    1.38
    ورك
    1.37
    ri
    1.32
    وريا
    1.31
    علي
    1.30
    افي
    1.30
    la
    1.26
    Activations Density 0.000%

    No Known Activations