© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7550
    Prev
    Next
    INDEX
    Explanations

    mentions of named geographic regions and general locations in terms of the

    oai_token-act-pair · gemini-2.0-flash

    geographical locations or administrative areas

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     calldata
    -0.55
    fjspx
    -0.52
    Hentet
    -0.52
    neté
    -0.51
     táctil
    -0.50
     Normdatei
    -0.49
     quirúrg
    -0.48
    ::_('
    -0.48
     CHAPITRE
    -0.48
     Profitez
    -0.47
    POSITIVE LOGITS
     state
    0.67
    Kanpo
    0.63
    MemoryWarning
    0.60
     city
    0.59
    ulle
    0.57
    
    0.56
     greater
    0.56
    PageRoute
    0.53
     Upper
    0.53
    ReusableCell
    0.51
    Activations Density 0.825%

    No Known Activations