© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 98851
    Prev
    Next
    INDEX
    Explanations

    performance timings issues

    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_16_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
     வித
    0.55
     richly
    0.53
    on
    0.53
    ona
    0.53
    ão
    0.52
    cida
    0.52
    éb
    0.52
    ด
    0.51
    ñ
    0.51
     c
    0.50
    POSITIVE LOGITS
    Pose
    0.55
    ведении
    0.54
    leden
    0.53
    Nuclear
    0.50
    Speak
    0.49
    LAND
    0.49
    ресенье
    0.49
    Thermal
    0.49
    Radio
    0.48
    Swim
    0.48
    Activations Density 0.009%

    No Known Activations