© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193499
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
     μεγ
    0.47
    writeFile
    0.47
    orche
    0.45
    pipelines
    0.42
    ش
    0.42
    WARNING
    0.42
     इंफॉर्मेशन
    0.42
    <0x97>
    0.41
    ون
    0.41
    ySpeed
    0.41
    POSITIVE LOGITS
     edilen
    0.52
     semasa
    0.50
     compact
    0.50
     toa
    0.49
    珴
    0.49
     Rasa
    0.49
     camada
    0.48
    仯
    0.48
     magnetic
    0.48
     suprem
    0.48
    Activations Density 0.000%

    No Known Activations