© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123006
    Prev
    Next
    INDEX
    Explanations

    nelarabine, nelnet, nelson sauvin, np-hard, hardness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     was
    0.58
    ৌশ
    0.57
    ampaikan
    0.55
     එම
    0.54
    }\,
    0.53
     않았
    0.52
     چندین
    0.52
     대한
    0.51
     জায়গা
    0.51
     twofold
    0.51
    POSITIVE LOGITS
    м
    1.05
    م
    0.89
    то
    0.88
    ي
    0.87
    n
    0.86
    ur
    0.78
    هي
    0.71
    ла
    0.70
    сто
    0.68
    يي
    0.68
    Activations Density 0.000%

    No Known Activations