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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259151
    Prev
    Next
    INDEX
    Explanations

    probability of selecting

    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
    sthe
    0.52
    azio
    0.51
    is
    0.47
    ong
    0.46
    angle
    0.44
     সাহ
    0.44
    asakan
    0.43
    -
    0.43
    でに
    0.42
    azole
    0.41
    POSITIVE LOGITS
     SupCt
    0.91
     Cllr
    0.84
     Confira
    0.83
    Ви
    0.80
     conceding
    0.77
     Если
    0.76
    کروچ
    0.76
     representada
    0.75
    clickView
    0.75
     Ви
    0.75
    Activations Density 0.002%

    No Known Activations