© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199167
    Prev
    Next
    INDEX
    Explanations

    smoke rings and formations

    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_12_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
    bea
    0.23
    Scholar
    0.22
    蚓
    0.21
    Bea
    0.21
    mActivity
    0.21
    tetra
    0.21
    neb
    0.20
    nestjs
    0.20
    <unused75>
    0.20
    راض
    0.20
    POSITIVE LOGITS
    りで
    0.23
     shocking
    0.22
     skull
    0.22
     alias
    0.22
     caricature
    0.21
     personnelle
    0.21
     Into
    0.21
    りと
    0.21
     काल्पनिक
    0.21
     ruido
    0.21
    Activations Density 0.000%

    No Known Activations