© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3712
    Prev
    Next
    INDEX
    Explanations

    what should i do

    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
     establecidos
    0.70
     variational
    0.64
    隰
    0.62
     inget
    0.62
     vanadium
    0.60
    ិត្ត
    0.59
    मान
    0.59
    ាតុ
    0.58
     ayarl
    0.58
     ole
    0.58
    POSITIVE LOGITS
    ه
    0.64
    ו
    0.62
    त
    0.62
    ο
    0.61
    𝘰
    0.56
    an
    0.54
    ionario
    0.51
    কারীর
    0.50
    স
    0.50
    ے
    0.49
    Activations Density 0.034%

    No Known Activations