© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 335
    Prev
    Next
    INDEX
    Explanations

    c stdio functions like printf

    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_40_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
    㖘
    0.43
    PD
    0.41
    窅
    0.41
    DEM
    0.40
    NEUTRON
    0.38
     permeate
    0.38
    㐬
    0.38
    둠
    0.38
     DER
    0.37
    Golem
    0.37
    POSITIVE LOGITS
     printf
    1.49
    printf
    1.44
     fprintf
    1.21
    fprintf
    1.20
     scanf
    1.14
    scanf
    1.13
     sprintf
    1.00
    Printf
    0.99
    sprintf
    0.95
    Sprintf
    0.81
    Activations Density 0.036%

    No Known Activations