© 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. 122931
    Prev
    Next
    INDEX
    Explanations

    Ninja Turtles and company

    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
    '
    0.90
     Τ
    0.64
     материалов
    0.60
     اﻻ
    0.60
     проб
    0.59
     ресурс
    0.59
     campe
    0.59
    𝑁
    0.59
     cinco
    0.58
     એલ
    0.58
    POSITIVE LOGITS
    к
    0.67
    ล
    0.63
    u
    0.60
    ic
    0.57
    binghamton
    0.55
     അതിന്റെ
    0.53
    res
    0.51
    크
    0.51
    ائن
    0.51
     मिलाकर
    0.51
    Activations Density 0.001%

    No Known Activations