© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176137
    Prev
    Next
    INDEX
    Explanations

    cone cells

    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_20_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
    ächen
    0.48
    consent
    0.48
     আবদুল্লাহ
    0.45
    ﮟ
    0.43
    퓰
    0.41
    ukun
    0.41
     вона
    0.40
    쮿
    0.40
     دوس
    0.40
    ackerel
    0.40
    POSITIVE LOGITS
     आलोचना
    0.46
     acest
    0.45
     प्रस्ताव
    0.44
     filet
    0.43
     disappoint
    0.43
     mencion
    0.42
     tính
    0.41
     coiled
    0.40
     g
    0.40
     ফাইল
    0.40
    Activations Density 0.001%

    No Known Activations