© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5210
    Prev
    Next
    INDEX
    Explanations

    chance and probability

    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_3_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
    やかな
    2.29
    uette
    2.09
    ąć
    2.09
    会
    2.08
    bodyParser
    2.06
    Oro
    2.05
    𝐵
    2.04
     Damn
    2.03
     damn
    2.01
    やかに
    2.00
    POSITIVE LOGITS
    ل
    3.59
    ă
    2.60
    ва
    2.51
    ло
    2.50
    seiten
    2.45
    те
    2.44
    ल
    2.30
    ר
    2.10
    금
    2.04
    если
    2.04
    Activations Density 0.049%

    No Known Activations