© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80257
    Prev
    Next
    INDEX
    Explanations

    becoming increasingly

    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_0_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
    지
    1.46
    나
    1.41
     on
    1.18
    ↵
    1.17
    s
    1.17
    u
    1.15
    ulation
    1.11
    лло
    1.10
    지와
    1.07
    지의
    1.00
    POSITIVE LOGITS
    ول
    1.47
    ט
    1.46
    ме
    1.37
     desenvolv
    1.35
    ה
    1.35
    ag
    1.34
     produz
    1.27
    ב
    1.27
    ه
    1.22
    يل
    1.17
    Activations Density 0.005%

    No Known Activations