© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261059
    Prev
    Next
    INDEX
    Explanations

    fans and fan-related content

    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_5_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
    مانی
    1.44
     to
    1.41
    ной
    1.34
    ма
    1.30
    to
    1.26
    م
    1.20
     It
    1.19
    ו
    1.16
     I
    1.15
    кови
    1.13
    POSITIVE LOGITS
    \
    1.38
    ↵↵
    1.20
    ’
    1.15
     Zijn
    1.08
    Th
    1.03
    9
    1.03
    3
    1.02
    5
    1.02
    ه
    0.98
    '>{
    0.98
    Activations Density 0.002%

    No Known Activations