© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14808
    Prev
    Next
    INDEX
    Explanations

    present tense verbs being used as adjectives

    oai_token-act-pair · gemini-2.0-flash

    formal texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    parsedMessage
    -0.87
     للاسماء
    -0.77
    expandindo
    -0.74
    Geplaatst
    -0.65
     Everybody
    -0.62
     everybody
    -0.62
     متعلقه
    -0.60
    +#+#
    -0.60
    providedIn
    -0.59
     "..\..\..\
    -0.59
    POSITIVE LOGITS
    
    0.57
    whence
    0.48
     therefrom
    0.47
    mmate
    0.47
    AFFIRMED
    0.47
    pendium
    0.46
    prefs
    0.45
    rosoft
    0.45
    แก่
    0.44
     angef
    0.43
    Activations Density 3.172%

    No Known Activations