© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    ن
    1.16
    n
    1.12
    ረው
    1.11
    рили
    1.06
    y
    1.04
    бот
    1.03
    ви
    1.02
     Transaction
    0.99
    掌握
    0.99
    ويات
    0.98
    POSITIVE LOGITS
     inverso
    1.36
    ynth
    1.24
    eyen
    1.24
    ১
    1.20
    しかし
    1.18
    objectManager
    1.18
     pleinement
    1.18
    midnight
    1.17
    亞
    1.16
     monoxide
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.