© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5716
    Prev
    Next
    INDEX
    Explanations

    noun–noun combinations

    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_39_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
    óst
    0.46
    ᒡ
    0.45
     沒有
    0.44
     เพื่อน
    0.43
    ਟ
    0.43
    errorMessage
    0.42
    british
    0.42
     女
    0.42
     灬
    0.41
    र्च
    0.41
    POSITIVE LOGITS
     kip
    0.53
     envisaged
    0.51
     непре
    0.41
    дован
    0.41
     комп
    0.40
     marvell
    0.39
     poda
    0.39
    kip
    0.39
     envisage
    0.38
     затем
    0.38
    Activations Density 0.043%

    No Known Activations