© 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. 12293
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to objects, events and opinions found in user-generated support documentation or how-to style posts

    oai_token-act-pair · gemini-2.0-flash

    technical issues

    np_max-act-logits · gemini-2.0-flash

    say "verbs"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    LookAnd
    -0.70
    Added
    -0.63
     noqa
    -0.63
    got
    -0.63
     tartalomajánló
    -0.62
    gnac
    -0.62
    argout
    -0.61
     CanadaChoose
    -0.60
     Trouver
    -0.59
     ddelweddau
    -0.59
    POSITIVE LOGITS
    WriteTagHelper
    0.47
     VBox
    0.46
     חיצוניים
    0.43
     driven
    0.43
    ="@+
    0.43
    PageRoute
    0.41
     Jdbc
    0.41
    펴
    0.41
    VK
    0.41
    oia
    0.41
    Activations Density 12.520%

    No Known Activations