© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5434
    Prev
    Next
    INDEX
    Explanations

    articles, possessive pronouns, superlatives, and adjectives related to importance or effectiveness

    oai_token-act-pair · gemini-2.0-flash

    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_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
     ModelExpression
    -1.33
    
    -1.16
     Roskov
    -1.14
    IUrlHelper
    -1.10
     صوتيه
    -1.10
    tagHelperRunner
    -1.09
    AndEndTag
    -1.08
     Efq
    -1.08
     initComponents
    -1.07
    NameInMap
    -1.07
    POSITIVE LOGITS
     most
    1.63
    Most
    1.27
     Most
    1.18
    most
    1.09
     MOST
    1.02
     proper
    0.69
     right
    0.66
     correct
    0.65
    MOST
    0.60
     mest
    0.60
    Activations Density 3.293%

    No Known Activations