© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    code snippets using the split function to manipulate strings

    oai_token-act-pair · gemini-2.0-flash

    programming functions and variable manipulation

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

    Code string manipulation

    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
    AsUp
    -0.69
    íncia
    -0.59
    ORETICAL
    -0.51
    Glej
    -0.50
     Space
    -0.49
    adaptiveStyles
    -0.49
    ErrUnexpectedEOF
    -0.49
    Grüsse
    -0.49
    sizeCache
    -0.49
    XmlAccessorType
    -0.49
    POSITIVE LOGITS
    
    0.58
    migrationBuilder
    0.57
    }";
    0.56
    NameInMap
    0.56
     الحره
    0.54
    }';
    0.53
     intptr
    0.51
    >';
    0.51
    ScopeManager
    0.49
    /**
    0.49
    Activations Density 0.860%

    No Known Activations