© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16314
    Prev
    Next
    INDEX
    Explanations

    dependency versions

    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
     veiled
    0.41
    দ্র
    0.38
     கார்ப
    0.35
     carbur
    0.34
    ellant
    0.34
    ंपल
    0.33
     पत्ते
    0.33
    轉
    0.33
     тол
    0.33
    黑暗
    0.33
    POSITIVE LOGITS
    числе
    0.41
    asena
    0.38
    ambarkan
    0.36
    స్తున్నాయి
    0.35
    никова
    0.34
    жна
    0.33
     κον
    0.33
    ussian
    0.33
    yno
    0.32
    Mono
    0.32
    Activations Density 0.001%

    No Known Activations