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. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3996
    Prev
    Next
    INDEX
    Explanations

    and,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ात
    1.86
    به
    1.85
    ع
    1.80
    shoe
    1.78
    точ
    1.74
    eft
    1.68
     buah
    1.65
    م
    1.64
    ej
    1.63
     самому
    1.58
    POSITIVE LOGITS
     JLabel
    1.92
     raped
    1.89
    rnn
    1.80
    ﺽ
    1.79
    ormous
    1.77
    já
    1.73
     mandamus
    1.71
     acara
    1.70
    raged
    1.69
     doš
    1.68
    Activations Density 0.003%

    No Known Activations