© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7154
    Prev
    Next
    INDEX
    Explanations

    the prefix "pres" regardless of capitalization

    oai_token-act-pair · gemini-2.0-flash

    Pres

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    出版年
    -1.04
     Administrativna
    -1.02
    
    -1.00
     оригіналу
    -0.94
    verwijspagina
    -0.94
    rungsseite
    -0.94
     '\\;'
    -0.93
    WithIOException
    -0.93
    دانشنامهٔ
    -0.91
     nakalista
    -0.91
    POSITIVE LOGITS
    yth
    0.41
    y
    0.40
    um
    0.35
    .
    0.35
     (
    0.35
     du
    0.34
     um
    0.33
    *
    0.33
     M
    0.32
    ob
    0.32
    Activations Density 0.689%

    No Known Activations