© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258224
    Prev
    Next
    INDEX
    Explanations

    list separators

    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_10_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
     tomato
    0.46
     goals
    0.44
     savings
    0.43
     motivated
    0.43
     radial
    0.42
     meter
    0.42
    z
    0.42
     very
    0.42
     optimal
    0.41
     really
    0.40
    POSITIVE LOGITS
    Dónde
    0.50
    áno
    0.50
    சிரிய
    0.49
    decin
    0.48
    પાસ
    0.47
    Suk
    0.46
    Puede
    0.46
    明的
    0.46
    iót
    0.45
    稣
    0.45
    Activations Density 0.086%

    No Known Activations