© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74885
    Prev
    Next
    INDEX
    Explanations

    ...

    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_31_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
     Both
    0.38
     tetrach
    0.37
     lih
    0.35
     幅
    0.34
     enemy
    0.34
     belt
    0.34
     Belt
    0.34
     उड़
    0.34
     steps
    0.33
     Spectral
    0.33
    POSITIVE LOGITS
    스티
    0.38
    欤
    0.36
     últimos
    0.35
    டன்
    0.35
     څرنګ
    0.34
    பின்
    0.34
    שט
    0.34
    inke
    0.34
    adan
    0.34
    ओके
    0.34
    Activations Density 0.003%

    No Known Activations