© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    indicates existence

    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_40_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
    jero
    0.37
    ించాలి
    0.37
     Bias
    0.36
    子公司
    0.36
     に対して
    0.35
    дации
    0.35
    䒺
    0.35
     өчен
    0.35
     Rag
    0.35
    ﹚
    0.35
    POSITIVE LOGITS
     olduğunu
    1.55
     olmadığını
    1.38
     있다는
    1.30
    であることを
    1.24
    임을
    1.17
     ఉందని
    1.11
     असल्याचे
    1.09
     බව
    1.06
    한다는
    1.05
     असल्याची
    1.02
    Activations Density 0.007%

    No Known Activations