© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101707
    Prev
    Next
    INDEX
    Explanations

    Times New Roman font

    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_14_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
     эксперти
    0.65
     та
    0.63
     Ла
    0.63
     службу
    0.62
     ὑ
    0.61
     sécurité
    0.61
     đèn
    0.60
     яких
    0.59
    타
    0.59
     Сури
    0.59
    POSITIVE LOGITS
    0
    0.58
    کل
    0.54
    des
    0.53
    সের
    0.52
    Harga
    0.52
    꼴
    0.52
    োর
    0.51
    name
    0.51
    ridden
    0.50
    R
    0.50
    Activations Density 0.000%

    No Known Activations