© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107392
    Prev
    Next
    INDEX
    Explanations

    information extraction

    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
    ين
    2.05
     aujourd
    1.65
    viii
    1.62
    self
    1.59
    That
    1.55
    스
    1.55
     doesn
    1.52
    Figura
    1.52
    ABILITIES
    1.51
     он
    1.49
    POSITIVE LOGITS
    ;
    1.42
     country
    1.21
     driver
    1.09
    :
    1.09
     shouldn
    1.07
    iel
    1.05
     week
    1.04
    },
    1.00
     Labour
    0.96
     dell
    0.96
    Activations Density 0.003%

    No Known Activations