© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133622
    Prev
    Next
    INDEX
    Explanations

    mitigar, mitologías

    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_1_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
     that
    1.41
     of
    1.39
     at
    1.18
     to
    1.15
     with
    1.11
     was
    1.09
    ,
    1.07
     que
    1.01
     it
    1.00
     which
    0.99
    POSITIVE LOGITS
    ↵
    1.48
    न
    0.96
    ᅨ
    0.83
    ه
    0.80
     Phó
    0.79
     Մ
    0.78
    ти
    0.77
    ა
    0.77
    ້
    0.75
    Middle
    0.73
    Activations Density 0.000%

    No Known Activations