© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219551
    Prev
    Next
    INDEX
    Explanations

    numbers and 'value' followed by more numbers or 'of'

    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
     যথার্থ
    0.20
     boar
    0.19
     معروف
    0.18
    ப்பர்
    0.18
    較
    0.18
     vieron
    0.18
     byl
    0.18
     była
    0.18
    ፔ
    0.18
    дир
    0.18
    POSITIVE LOGITS
     Hoch
    0.23
     [...]
    0.20
     inflater
    0.20
    IZE
    0.20
    Fin
    0.19
     fintech
    0.19
     Fin
    0.19
    emerald
    0.19
     प्रिया
    0.19
    emento
    0.19
    Activations Density 0.001%

    No Known Activations