© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99198
    Prev
    Next
    INDEX
    Explanations

    veins of

    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_16_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
     hallmarks
    0.56
    \
    0.51
    “
    0.47
     hallmark
    0.47
    ing
    0.44
     nurturing
    0.44
    M
    0.44
     unclear
    0.44
     temos
    0.44
     flowchart
    0.44
    POSITIVE LOGITS
    ů
    0.54
    izzando
    0.54
     prodotto
    0.51
    SpriteCollision
    0.50
    mato
    0.49
    බා
    0.48
    zyma
    0.47
    Simulation
    0.47
    şe
    0.46
    ütü
    0.46
    Activations Density 0.000%

    No Known Activations