© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172702
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with + and -

    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_20_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
    atori
    0.44
    ୬
    0.42
    ulan
    0.40
    amatan
    0.39
    ನಿ
    0.39
    дето
    0.38
     }.
    0.38
    ervation
    0.38
     delineation
    0.38
    污染
    0.37
    POSITIVE LOGITS
    スカ
    0.44
     clock
    0.44
     ኩ
    0.42
     gamle
    0.41
     strand
    0.41
     Stall
    0.41
    Clock
    0.40
     sk
    0.39
     części
    0.39
     me
    0.39
    Activations Density 0.008%

    No Known Activations