Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1631
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to scans of tumors including the word 'lesion'

    oai_token-act-pair · gemini-2.0-flash

    Medical/biological research texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ทธิ
    -0.54
    ValueStyle
    -0.53
    }*/
    
    -0.53
     FSA
    -0.51
     TimeUnit
    -0.50
    apunov
    -0.50
     IES
    -0.48
    )}</
    -0.48
    μως
    -0.47
     distanciation
    -0.47
    POSITIVE LOGITS
    Portály
    0.66
    fjspx
    0.66
     disambiguazione
    0.63
    NameInMap
    0.63
    migrationBuilder
    0.61
    ArgsConstructor
    0.61
     MotionEvent
    0.60
     EconPapers
    0.59
    Composable
    0.58
     {?>
    0.58
    Activations Density 6.057%

    No Known Activations