© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5270
    Prev
    Next
    INDEX
    Explanations

    verbs of motion, especially "come" and "back"

    oai_token-act-pair · gemini-2.0-flash

    come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     препратки
    -0.59
     struck
    -0.55
    XmlAccessType
    -0.50
     энциклопедия
    -0.49
     فريبيس
    -0.47
    ритори
    -0.47
    rav
    -0.47
    igenous
    -0.47
     Monte
    -0.46
    IVITY
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.83
    MigrationBuilder
    0.59
    #+#
    0.59
     Réponses
    0.58
    المكان
    0.57
     overeen
    0.56
    SequentialGroup
    0.56
     crashing
    0.55
    Билгалдахарш
    0.54
    มาะ
    0.54
    Activations Density 0.591%

    No Known Activations