© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229558
    Prev
    Next
    INDEX
    Explanations

    equations with 'x'

    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_6_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
     (
    1.00
    ↵↵
    0.87
    ot
    0.87
    S
    0.86
    R
    0.86
    ans
    0.76
    ir
    0.75
    rom
    0.70
    Server
    0.70
    ile
    0.67
    POSITIVE LOGITS
    t
    1.16
    ک
    1.10
    ຜະລິດຕະພັນ
    1.02
    к
    0.92
     к
    0.91
    л
    0.90
     amperes
    0.89
    ພວກເຮົາ
    0.87
    sai
    0.86
    ກ
    0.86
    Activations Density 0.006%

    No Known Activations