© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43844
    Prev
    Next
    INDEX
    Explanations

    hello world

    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_13_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
    𝓢
    0.46
    ５
    0.45
    ዎታል
    0.45
     संघर्ष
    0.43
     सूजन
    0.43
    Sholes
    0.42
    Handbook
    0.42
    𝘞
    0.41
    歌
    0.41
    ８
    0.41
    POSITIVE LOGITS
     dreadful
    0.47
     fe
    0.43
     arrog
    0.41
     ruled
    0.41
     slumped
    0.41
    uidade
    0.41
     gall
    0.40
     infe
    0.40
     el
    0.40
     dall
    0.39
    Activations Density 0.011%

    No Known Activations