© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32572
    Prev
    Next
    INDEX
    Explanations

    maximum tolerated dose

    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_31_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
     فوتبال
    0.41
     फुटबॉल
    0.40
     neh
    0.38
    囘
    0.38
    解釋
    0.37
     explaining
    0.37
     காதல்
    0.37
     domést
    0.36
     explains
    0.36
     футбо
    0.36
    POSITIVE LOGITS
    拓
    0.42
     hemicontinuous
    0.37
    랙
    0.37
     preparação
    0.36
     VIII
    0.36
     সক
    0.35
     worsened
    0.35
     caos
    0.35
    administered
    0.34
     snub
    0.33
    Activations Density 0.025%

    No Known Activations