© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167727
    Prev
    Next
    INDEX
    Explanations

    isolating compounds or reactions

    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_34_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
     leaves
    0.46
    leaves
    0.38
    ah
    0.37
     leaf
    0.37
     avem
    0.36
     Leaves
    0.36
     brigade
    0.36
    <0xF1>
    0.36
    leaf
    0.35
     stains
    0.35
    POSITIVE LOGITS
     能力
    0.39
     Identify
    0.39
    Refrigerator
    0.38
     তথ্য
    0.38
     Lorentz
    0.38
    故意
    0.38
    তথ্য
    0.38
     Prime
    0.37
     ఆట
    0.37
    物理
    0.37
    Activations Density 0.001%

    No Known Activations