© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99477
    Prev
    Next
    INDEX
    Explanations

    Titanic survival prediction

    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_16_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
     მთავ
    0.55
    ياب
    0.52
     огром
    0.52
    aps
    0.50
    тами
    0.50
    apak
    0.50
    <span>
    0.49
    تمام
    0.49
     masch
    0.49
    </a>
    0.48
    POSITIVE LOGITS
    VICIO
    0.46
    ené
    0.45
    ையிலும்
    0.44
     tué
    0.44
    ﮑ
    0.44
    ce
    0.43
     continúa
    0.43
    ဖွ
    0.43
    inée
    0.43
     bevorzug
    0.43
    Activations Density 0.002%

    No Known Activations