© 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. 157525
    Prev
    Next
    INDEX
    Explanations

    tyrosh

    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
    and
    1.48
    gan
    1.13
    cience
    1.13
    ght
    1.09
     have
    1.07
     acidity
    1.06
    cC
    1.06
    1
    1.05
    ight
    1.05
    can
    1.04
    POSITIVE LOGITS
    м
    1.38
    л
    1.21
    ാ
    1.16
    l
    1.15
    لای
    1.13
     valore
    1.13
     verificar
    1.09
    <0x0D>
    1.08
    ו
    1.05
    ro
    1.04
    Activations Density 0.000%

    No Known Activations