© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85803
    Prev
    Next
    INDEX
    Explanations

    Docker Swarm / Theft / Hills

    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_3_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
    U
    0.67
    AN
    0.64
    "}
    0.62
     season
    0.56
     deduce
    0.55
     striker
    0.54
    In
    0.54
    ];
    0.54
     shader
    0.52
     }
    0.52
    POSITIVE LOGITS
    ма
    0.67
    a
    0.60
    ા
    0.56
    setDisplay
    0.54
    форм
    0.53
    ați
    0.52
    磡
    0.52
    ه
    0.52
    崦
    0.52
    d
    0.51
    Activations Density 0.004%

    No Known Activations