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. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15165
    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_19_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
    하게
    0.69
     scenes
    0.68
     Wirk
    0.66
     Rec
    0.66
     Resist
    0.66
    경
    0.63
    וש
    0.63
    нце
    0.63
    铷
    0.63
     Modena
    0.62
    POSITIVE LOGITS
     leasing
    0.74
     convivial
    0.72
     becoming
    0.70
    ars
    0.70
    efeu
    0.70
     inferior
    0.69
     superior
    0.69
    frast
    0.68
     agreeing
    0.67
     ----------
    0.67
    Activations Density 0.000%

    No Known Activations