© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58274
    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_11_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
    r
    0.48
     EMI
    0.47
    an
    0.46
    lo
    0.45
    ról
    0.45
    ார்கள்
    0.45
     Turismo
    0.44
    h
    0.44
    aider
    0.43
    can
    0.42
    POSITIVE LOGITS
    \:
    0.52
     قناة
    0.49
    䢎
    0.48
     nodeList
    0.47
    探
    0.47
     पड़
    0.45
     altijd
    0.44
    怡
    0.44
     engage
    0.43
    EndZ
    0.43
    Activations Density 0.000%

    No Known Activations