© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14551
    Prev
    Next
    INDEX
    Explanations

    words in Croatian related to Facebook account creation and terms of service

    oai_token-act-pair · gemini-2.0-flash

    code, URLs, foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     for
    -0.67
     BorderRadius
    -0.57
     with
    -0.51
     to
    -0.51
     utafitiHapana
    -0.51
    protoimpl
    -0.50
    lujah
    -0.49
    lossians
    -0.47
    aryen
    -0.46
    Erreferentziak
    -0.45
    POSITIVE LOGITS
     kaarangay
    0.69
     parseFrom
    0.68
    /***/
    0.57
    SceneManagement
    0.54
     Mortuary
    0.52
     Locker
    0.51
    oredCriteria
    0.50
    rungsseite
    0.50
     ExecuteAsync
    0.50
     intit
    0.50
    Activations Density 0.226%

    No Known Activations