© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    sequences containing words related to Facebook, mobile phones, submitting data and text messages

    oai_token-act-pair · gemini-2.0-flash

    Facebook SMS authentication

    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
     and
    -0.59
     typelib
    -0.58
     ComVisible
    -0.52
    mapStateToProps
    -0.51
    complexContent
    -0.46
     Roskov
    -0.45
     désolés
    -0.43
     with
    -0.43
    mbggenerated
    -0.42
    protoimpl
    -0.42
    POSITIVE LOGITS
    numerusform
    0.66
     gmina
    0.59
    Den
    0.58
     koje
    0.56
     která
    0.56
     Den
    0.56
    tences
    0.56
    هات
    0.55
    thâu
    0.54
     Ey
    0.54
    Activations Density 0.814%

    No Known Activations