© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143749
    Prev
    Next
    INDEX
    Explanations

    season summary

    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_0_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
    اں
    1.38
    с
    1.33
    ви
    1.27
     primordial
    1.20
    ა
    1.17
     luxury
    1.15
     choir
    1.13
    اً
    1.12
     modular
    1.10
     plush
    1.09
    POSITIVE LOGITS
    k
    2.08
    ص
    1.55
    ك
    1.47
    kette
    1.46
    ts
    1.41
    tt
    1.34
    ca
    1.32
    tttt
    1.30
     on
    1.30
    ties
    1.28
    Activations Density 0.001%

    No Known Activations