© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13068
    Prev
    Next
    INDEX
    Explanations

    sentences containing a verb

    oai_token-act-pair · gemini-2.0-flash

    Positive adjectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IUrlHelper
    -1.04
    MigrationBuilder
    -0.85
    featureID
    -0.84
     للاسماء
    -0.83
    principalTable
    -0.81
    ValueStyle
    -0.80
     Normdatei
    -0.80
     الحره
    -0.80
    
    -0.77
    abestanden
    -0.75
    POSITIVE LOGITS
     excellent
    0.65
     accidental
    0.59
     random
    0.58
     wonderful
    0.58
     unintentional
    0.57
     significant
    0.56
     comprehensive
    0.54
     nice
    0.54
     meticulous
    0.54
     continuous
    0.53
    Activations Density 4.109%

    No Known Activations