© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11847
    Prev
    Next
    INDEX
    Explanations

    URLs containing "http", "server", "mike", "www", "phil", "com", "github", "users", "visual studio" and file names

    oai_token-act-pair · gemini-2.0-flash

    URL/code special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++
    
    -0.22
    )*/
    -0.22
     سكانية
    -0.21
     tartalomajánló
    -0.21
    )•
    -0.20
    __":
    
    -0.20
    URLException
    -0.20
    InputBorder
    -0.19
     Roskov
    -0.18
    }$​
    -0.18
    POSITIVE LOGITS
    ėjimo
    0.77
    XtraReports
    0.72
     recommandons
    0.72
     tarko
    0.71
     helyez
    0.71
     atve
    0.71
     lisäksi
    0.70
     trasparente
    0.70
    ėjimas
    0.70
     actionTypes
    0.70
    Activations Density 3.363%

    No Known Activations