© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16181
    Prev
    Next
    INDEX
    Explanations

    prime number generation

    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_34_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
    的には
    0.38
     Measures
    0.38
    実際に
    0.37
     <-
    0.37
     લાઇ
    0.37
    🐣
    0.37
    Inputs
    0.36
    吉
    0.36
     رو
    0.35
     Shop
    0.35
    POSITIVE LOGITS
     vacaciones
    0.44
    íbrio
    0.41
    spr
    0.40
    gação
    0.40
     torso
    0.39
     cathode
    0.38
     adjustment
    0.38
     rumor
    0.37
     boric
    0.37
     resistor
    0.37
    Activations Density 0.011%

    No Known Activations