© 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. 8099
    Prev
    Next
    INDEX
    Explanations

    words related to bicycle tire repair

    oai_token-act-pair · gemini-2.0-flash

    fixing/repairing devices

    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
    RegressionTest
    -0.67
     متعلقه
    -0.64
    AutoScaleMode
    -0.63
    PYX
    -0.60
     GreatSchools
    -0.59
    LookAnd
    -0.58
     Numerade
    -0.57
    Browsable
    -0.57
     consentement
    -0.56
     resourceCulture
    -0.56
    POSITIVE LOGITS
    ContentAsync
    0.55
    [](
    0.54
    ஈ
    0.51
     ſp
    0.50
     purpoſe
    0.49
     ſtate
    0.48
     pleaſure
    0.48
     iſt
    0.46
    ocidad
    0.45
    Depot
    0.45
    Activations Density 18.877%

    No Known Activations