© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149141
    Prev
    Next
    INDEX
    Explanations

    say "-a" or "-i"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     aram
    0.41
     THEIR
    0.40
     Al
    0.40
     Ле
    0.39
    SIZ
    0.38
     arn
    0.38
     (#
    0.37
     LEG
    0.37
     เบ
    0.36
    States
    0.36
    POSITIVE LOGITS
    eh
    0.44
    ekra
    0.42
    e
    0.42
    kjav
    0.40
    volvimento
    0.40
    dv
    0.40
    rotnie
    0.39
    eya
    0.38
     Raha
    0.38
    valment
    0.37
    Activations Density 0.000%

    No Known Activations