© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3735
    Prev
    Next
    INDEX
    Explanations

    explaining by breaking down

    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
    с
    0.53
     ovales
    0.48
    स
    0.47
    ν
    0.45
    quele
    0.43
     roy
    0.43
    de
    0.43
    い
    0.42
    со
    0.41
     auparavant
    0.41
    POSITIVE LOGITS
     তারপরে
    0.53
     никаких
    0.52
    eer
    0.51
     whatnot
    0.49
    Cumulative
    0.49
    birds
    0.48
    considering
    0.48
    erson
    0.47
    MBA
    0.47
     NOTHING
    0.47
    Activations Density 0.326%

    No Known Activations