© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171338
    Prev
    Next
    INDEX
    Explanations

    beer and cola types

    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_20_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
    orphic
    0.52
    emph
    0.46
    brid
    0.44
    erro
    0.44
    omt
    0.44
    utton
    0.44
    encour
    0.44
    蝙
    0.44
    ffiti
    0.43
    panel
    0.43
    POSITIVE LOGITS
     নিয়ম
    0.45
     বসবাস
    0.43
     Maser
    0.42
     SIST
    0.41
     gême
    0.41
     země
    0.41
     settimane
    0.40
    ствима
    0.40
    📋
    0.40
    انيا
    0.39
    Activations Density 0.000%

    No Known Activations