© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261385
    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_22_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
     দেখার
    0.48
     >
    0.47
     Keeps
    0.46
     মোটরসাই
    0.44
    :":
    0.44
     Conflict
    0.43
     prevail
    0.43
     keeps
    0.43
     stays
    0.43
     prevails
    0.43
    POSITIVE LOGITS
     DS
    0.47
    frü
    0.47
    derived
    0.44
     funkt
    0.44
    sb
    0.43
     skrev
    0.43
    悰
    0.43
     tomonidan
    0.42
     väx
    0.41
     derived
    0.41
    Activations Density 0.000%

    No Known Activations