© 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. 5604
    Prev
    Next
    INDEX
    Explanations

    enter after opening parenthesis

    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
    ০
    1.74
     piss
    1.64
    magenta
    1.61
    ǫ
    1.61
     cameraId
    1.61
     efect
    1.60
    gtr
    1.58
    eighth
    1.52
     unpaired
    1.52
     fris
    1.50
    POSITIVE LOGITS
    tedir
    1.81
     tanto
    1.71
    ної
    1.54
    heter
    1.46
    اي
    1.46
     něj
    1.44
    फ
    1.43
    是
    1.41
     totaled
    1.40
     је
    1.39
    Activations Density 0.004%

    No Known Activations