© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161770
    Prev
    Next
    INDEX
    Explanations

    [INTENT] brackets

    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_2_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
    та
    1.16
    0
    1.07
    ן
    1.04
    the
    1.01
     was
    1.00
    ాల
    0.98
    ру
    0.98
    s
    0.97
     and
    0.97
    ో
    0.96
    POSITIVE LOGITS
    イ
    0.99
    اری
    0.91
    ए
    0.91
    م
    0.91
     यू
    0.90
    न
    0.89
    И
    0.89
    i
    0.89
    Α
    0.88
     دی
    0.87
    Activations Density 0.000%

    No Known Activations