© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201352
    Prev
    Next
    INDEX
    Explanations

    candlestick patterns

    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_6_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
    es
    1.63
    s
    1.62
    in
    1.49
    ad
    1.37
    d
    1.34
    na
    1.20
    is
    1.17
    im
    1.17
    em
    1.17
    c
    1.17
    POSITIVE LOGITS
    р
    0.93
    ן
    0.92
     supremely
    0.88
     који
    0.86
    рта
    0.84
     chở
    0.82
    FFECT
    0.80
    볍
    0.80
     चांगले
    0.79
    ლ
    0.78
    Activations Density 0.000%

    No Known Activations