© 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. 9014
    Prev
    Next
    INDEX
    Explanations

    sentences where a person is quoted, or is making a statement

    oai_token-act-pair · gemini-2.0-flash

    someone speaking

    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
     add
    -0.99
     Add
    -0.98
    add
    -0.94
     Addition
    -0.93
    Add
    -0.92
     adding
    -0.92
     ADD
    -0.91
     añadir
    -0.83
     Adding
    -0.82
     addition
    -0.79
    POSITIVE LOGITS
     CreateTagHelper
    0.75
    MessageTagHelper
    0.74
    WriteTagHelper
    0.73
    findpost
    0.67
    tvguidetime
    0.64
     跳转至
    0.63
     Jefus
    0.63
     poffible
    0.62
    }{*}{
    0.62
     Diſ
    0.61
    Activations Density 9.091%

    No Known Activations