© 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. 410
    Prev
    Next
    INDEX
    Explanations

    instances where a person or organization is offering a service to someone

    oai_token-act-pair · gemini-2.0-flash

    Business/technical assistance

    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
    tvguidetime
    -0.65
    verwijspagina
    -0.62
    VersionUID
    -0.59
    dehydes
    -0.56
    ंदीखरीदारी
    -0.53
     تانيه
    -0.51
     Gave
    -0.50
    ContentAsync
    -0.50
    #+#
    -0.49
    GIVE
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.59
     NgModule
    0.54
     NSCoder
    0.52
    Personensuche
    0.50
    ConstraintMaker
    0.50
    DataSnapshot
    0.47
     jsPsych
    0.46
    IonicModule
    0.46
    انيف
    0.45
     teil
    0.45
    Activations Density 5.727%

    No Known Activations