© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18164
    Prev
    Next
    INDEX
    Explanations

    tumor or lump

    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
     посу
    0.48
     ditches
    0.45
     furnace
    0.41
     LAV
    0.39
     প্রবাসী
    0.39
     dard
    0.38
    攽
    0.38
    살
    0.38
     কার্য
    0.37
     canales
    0.37
    POSITIVE LOGITS
     tumours
    0.95
     tumour
    0.91
     tumeur
    0.91
     tumors
    0.85
     tumor
    0.84
     tumeurs
    0.83
    肿瘤
    0.79
    tumor
    0.76
     neoplas
    0.71
     cancerous
    0.70
    Activations Density 0.036%

    No Known Activations