© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245542
    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_11_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
    ../../
    1.23
     samt
    1.20
     wrinkled
    1.18
     immaterial
    1.14
     novelists
    1.11
    ສໍາ
    1.10
     heim
    1.08
     spiritual
    1.07
    ../../../
    1.06
    TAT
    1.06
    POSITIVE LOGITS
    нага
    1.38
    largest
    1.26
    excellence
    1.25
    d
    1.23
    l
    1.21
    b
    1.18
    soever
    1.18
    ths
    1.13
    ponents
    1.12
    rawn
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.