Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 244515
    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
    a
    1.53
    t
    1.30
    J
    1.21
    K
    1.19
    g
    1.15
    aula
    1.13
    tru
    1.12
    aç
    1.09
    y
    1.08
     loro
    1.07
    POSITIVE LOGITS
     shelving
    1.35
     таки
    1.27
    祸
    1.26
    勵
    1.25
     firewood
    1.24
    ưởng
    1.21
     tooling
    1.21
     conformance
    1.20
    ayutt
    1.20
     taz
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.