© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1953
    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_40_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
    brad
    0.44
     Accurate
    0.36
    allenges
    0.36
     되겠죠
    0.35
    怵
    0.35
     contatto
    0.33
     ยาว
    0.33
    쏠
    0.33
    ignores
    0.33
    zey
    0.32
    POSITIVE LOGITS
     believe
    1.74
    Believe
    1.58
     believes
    1.57
    believe
    1.55
     belief
    1.54
     Believe
    1.53
    相信
    1.48
     believer
    1.44
     believing
    1.41
     believed
    1.32
    Activations Density 0.085%

    No Known Activations