© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6527
    Prev
    Next
    INDEX
    Explanations

    km/h

    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_39_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
    Group
    0.39
     Group
    0.39
     GROUP
    0.39
     materiais
    0.38
    Grouping
    0.38
    GROUP
    0.38
    탤
    0.37
    资产
    0.36
     responsável
    0.36
     গ্রুপ
    0.36
    POSITIVE LOGITS
    atra
    0.44
    htra
    0.38
    wati
    0.37
    ﻒ
    0.36
    ottam
    0.35
    abwe
    0.34
     backpacking
    0.34
     deg
    0.34
    ogen
    0.34
    atti
    0.34
    Activations Density 0.001%

    No Known Activations