© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230507
    Prev
    Next
    INDEX
    Explanations

    occurrences after a preceding event

    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_6_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
    t
    1.27
    ل
    1.17
    و
    1.15
    л
    1.10
    f
    0.95
    لر
    0.94
    ح
    0.92
    r
    0.91
     in
    0.90
    ли
    0.89
    POSITIVE LOGITS
     altre
    0.92
    <unused2140>
    0.91
     viele
    0.90
     quero
    0.89
    śmy
    0.87
     irgendwie
    0.86
     putern
    0.86
     escribir
    0.84
    enced
    0.84
    >:
    0.84
    Activations Density 0.001%

    No Known Activations