© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 78295
    Prev
    Next
    INDEX
    Explanations

    tourist attractions and itineraries

    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_31_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
     waveform
    0.39
    ശ്ച
    0.36
     waveforms
    0.36
    าล
    0.35
     toppings
    0.34
    andled
    0.34
    $/.
    0.33
    HUD
    0.33
    স্তন
    0.33
    Monster
    0.33
    POSITIVE LOGITS
    FEATURE
    0.46
     FEATURE
    0.41
     শোনা
    0.38
     વિદ્યાર્થી
    0.36
     IMPACT
    0.35
     >>
    0.35
     экскур
    0.35
     -->
    0.35
    Feature
    0.34
     Does
    0.34
    Activations Density 0.008%

    No Known Activations