© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 159703
    Prev
    Next
    INDEX
    Explanations

    chiaroscuro

    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
    ן
    1.55
    า
    1.40
    ی
    1.21
    за
    1.20
    горь
    1.16
    सी
    1.08
    ری
    1.08
    ıya
    1.06
    де
    1.04
    и
    1.02
    POSITIVE LOGITS
    ב
    1.48
    >
    1.41
    د
    1.38
    w
    1.36
    يل
    1.30
    h
    1.27
    ون
    1.19
    其他
    1.16
    r
    1.16
    uk
    1.12
    Activations Density 0.000%

    No Known Activations