© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    words beginning with the letters "Kay", "Ay", "Jay", or containing "ay"

    oai_token-act-pair · gemini-2.0-flash

    Names starting with Kay/Ay/Jay

    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
    ArrowToggle
    -0.69
    LookAnd
    -0.68
     Normdatei
    -0.68
    NamedQueries
    -0.65
    __*/
    -0.65
     CreateTagHelper
    -0.63
    DebuggerNonUser
    -0.62
     expéri
    -0.61
    featureID
    -0.61
     cerrado
    -0.60
    POSITIVE LOGITS
    Scénario
    0.52
     autorytatywna
    0.49
    CPtr
    0.45
    el
    0.43
    MPN
    0.43
     led
    0.42
     ins
    0.41
    enne
    0.41
    —.
    0.40
     imageNamed
    0.39
    Activations Density 0.355%

    No Known Activations