© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170588
    Prev
    Next
    INDEX
    Explanations

    words after "elekt", "from", "die"

    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_20_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
     fury
    0.47
    Awesome
    0.44
     Furious
    0.43
     violent
    0.43
     Awesome
    0.42
     average
    0.41
     tip
    0.41
    宵
    0.40
     Firebase
    0.39
     kill
    0.39
    POSITIVE LOGITS
    <unused2115>
    0.42
    িনের
    0.40
    interpr
    0.40
    ]",
    0.40
    \|\
    0.39
    ⚉
    0.39
    ray
    0.38
    റ്റം
    0.38
    텁
    0.38
     통합
    0.38
    Activations Density 0.000%

    No Known Activations