© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     쓰
    0.39
    कांड
    0.38
    ..
    0.38
     علامه
    0.38
    timers
    0.37
    emde
    0.36
    limb
    0.36
    Proced
    0.36
     unpleasant
    0.36
    branch
    0.36
    POSITIVE LOGITS
    ucco
    0.41
    ovation
    0.40
     высокая
    0.40
    鑿
    0.40
     антенна
    0.39
    櫓
    0.38
     boldly
    0.38
     పు
    0.38
     grandeza
    0.37
     एकज
    0.37
    Activations Density 0.000%

    No Known Activations