© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164209
    Prev
    Next
    INDEX
    Explanations

    examining sales funnel

    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
     ইন্টারনেট
    0.46
     الإنترنت
    0.44
    互联网
    0.40
     benefici
    0.39
    <unused19>
    0.38
    internet
    0.38
    ➹
    0.38
    බ්
    0.38
    তুম
    0.37
     Pilates
    0.37
    POSITIVE LOGITS
    uluh
    0.43
     pressures
    0.37
     Prospective
    0.37
    股价
    0.36
     conductors
    0.36
     States
    0.36
     inger
    0.36
    angered
    0.35
     выступа
    0.35
     testifying
    0.35
    Activations Density 0.003%

    No Known Activations