© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260375
    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
     troubled
    1.07
    N
    1.04
    новый
    0.93
    an
    0.93
     ausge
    0.92
    шому
    0.91
     slopes
    0.89
    نیا
    0.89
    Е
    0.87
    E
    0.86
    POSITIVE LOGITS
    
    1.50
    assertSame
    1.34
    
    1.28
     پوکر
    1.23
    assertThat
    1.22
    %;
    1.21
    colgroup
    1.20
    鹂
    1.20
    góc
    1.18
     všet
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.