© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6042
    Prev
    Next
    INDEX
    Explanations

    words starting with "mis" or "fore"

    oai_token-act-pair · gemini-2.0-flash

    prefixes "mis" and "fore"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ma
    -0.57
    movable
    -0.47
    erves
    -0.46
    interpreted
    -0.45
    fak
    -0.45
     ha
    -0.44
     hierbas
    -0.44
    ro
    -0.44
    ;#
    -0.43
    ember
    -0.43
    POSITIVE LOGITS
    FormTagHelper
    0.70
    tagHelperRunner
    0.69
    ControllerAdvice
    0.66
     متعلقه
    0.65
     Efq
    0.65
     utafitiHapana
    0.65
    AnimationsModule
    0.64
     Мексичка
    0.64
     fubject
    0.64
     الحره
    0.63
    Activations Density 1.294%

    No Known Activations