© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166816
    Prev
    Next
    INDEX
    Explanations

    perpendicular to

    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_34_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
    ostat
    0.35
     comfortable
    0.34
     rhythm
    0.34
     рит
    0.34
     princípio
    0.33
    蒯
    0.33
    comfortable
    0.33
     favourable
    0.33
    achtung
    0.33
    順
    0.33
    POSITIVE LOGITS
     রেকর্ড
    0.42
    வுகளை
    0.39
    䝬
    0.38
     Paw
    0.37
     Bao
    0.36
     Turquie
    0.36
    퓸
    0.36
     বুল
    0.36
     구축
    0.36
     जावा
    0.35
    Activations Density 0.001%

    No Known Activations