© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    words related to Facebook account login and verification, especially those related to phone numbers and error messages

    oai_token-act-pair · gemini-2.0-flash

    AccountKit usage

    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
    IA
    -0.50
    inola
    -0.49
     dép
    -0.49
    lia
    -0.48
     NIA
    -0.47
     venons
    -0.47
    ya
    -0.47
    jeka
    -0.47
    jah
    -0.46
    nesia
    -0.46
    POSITIVE LOGITS
     estimés
    0.69
     مشين
    0.69
    wy
    0.66
    agy
    0.64
    expandindo
    0.64
    umy
    0.63
     beginnetje
    0.63
    Jeografia
    0.62
    iry
    0.60
     Ory
    0.60
    Activations Density 0.450%

    No Known Activations