© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217946
    Prev
    Next
    INDEX
    Explanations

    hidden

    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
    ята
    0.32
    terror
    0.29
     \
    0.28
    roft
    0.28
    quat
    0.27
     Hornet
    0.27
     In
    0.27
    *"
    0.27
    lips
    0.27
    roke
    0.26
    POSITIVE LOGITS
     visible
    0.40
     superficial
    0.32
     visibles
    0.32
     recourse
    0.31
     observable
    0.29
    Visible
    0.29
     apparent
    0.29
     reader
    0.29
     conspicuous
    0.28
     visibly
    0.28
    Activations Density 0.028%

    No Known Activations