© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159102
    Prev
    Next
    INDEX
    Explanations

    Sin embargo

    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
    мости
    1.08
    '
    1.06
    ↵
    1.05
    ו
    0.99
    ینہ
    0.96
    期の
    0.93
    来
    0.93
    رین
    0.88
    íř
    0.87
    و
    0.86
    POSITIVE LOGITS
     was
    1.30
     {
    1.16
     the
    1.15
     is
    1.10
     are
    1.08
    та
    1.08
    ब
    1.07
     this
    1.06
     be
    1.05
    ");
    1.04
    Activations Density 0.000%

    No Known Activations