© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15272
    Prev
    Next
    INDEX
    Explanations

    words related to gears, shifting, and driving modes in motor vehicles

    oai_token-act-pair · gemini-2.0-flash

    technical operating modes

    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
     Mode
    -2.42
     mode
    -2.39
    Mode
    -2.36
    mode
    -2.34
     MODE
    -2.19
     modes
    -2.17
     Modes
    -2.16
    modes
    -2.05
    MODE
    -2.03
    Modes
    -1.98
    POSITIVE LOGITS
    ])));
    0.60
    liosis
    0.48
     personnalisée
    0.46
    pfung
    0.46
     sucedido
    0.44
     Theſe
    0.44
     gehad
    0.44
    tagHelperRunner
    0.43
     proberen
    0.43
     mourut
    0.41
    Activations Density 1.235%

    No Known Activations