© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196610
    Prev
    Next
    INDEX
    Explanations

    whisky expert

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    }_{+}^{
    0.38
     heir
    0.37
    គេ
    0.37
     realist
    0.37
     snippetHide
    0.37
    wood
    0.36
     احتيا
    0.36
     تعدى
    0.36
    helf
    0.36
    ]|[
    0.36
    POSITIVE LOGITS
     لخ
    0.41
    Co
    0.38
    таю
    0.38
    koľ
    0.38
    ুত
    0.37
     Infl
    0.37
    aceous
    0.36
    ငံ
    0.36
    Chill
    0.35
     aero
    0.35
    Activations Density 0.004%

    No Known Activations