© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11962
    Prev
    Next
    INDEX
    Explanations

    the name Ramona and Ram

    oai_token-act-pair · gemini-2.0-flash

    Ram

    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
    wa
    -0.54
    wok
    -0.51
    WA
    -0.49
     Marc
    -0.49
    arda
    -0.48
     pede
    -0.48
    ViewStyle
    -0.48
    OfBirth
    -0.47
     Oph
    -0.47
    Mar
    -0.46
    POSITIVE LOGITS
    onAttach
    0.69
    exitRule
    0.69
     ChromeDriver
    0.68
     estimés
    0.68
    IUrlHelper
    0.66
    idavit
    0.57
    TemporalType
    0.57
    medriver
    0.55
    withIdentifier
    0.54
     Roskov
    0.54
    Activations Density 0.533%

    No Known Activations