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. 4014
    Prev
    Next
    INDEX
    Explanations

    astronomical objects and concepts

    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
    Cic
    0.61
    uristic
    0.60
    Coordinates
    0.59
    Coordinator
    0.56
    {"
    0.54
    wipe
    0.53
     savait
    0.53
    nq
    0.53
    Geo
    0.53
    lude
    0.52
    POSITIVE LOGITS
    𝓪
    0.84
     spotting
    0.74
     refracted
    0.68
     intimately
    0.67
    𝓾
    0.67
    at
    0.66
    ≾
    0.65
     repayment
    0.64
    你应该
    0.64
     simplices
    0.64
    Activations Density 0.158%

    No Known Activations