© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12366
    Prev
    Next
    INDEX
    Explanations

    negations, especially those related to political issues

    oai_token-act-pair · gemini-2.0-flash

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    principalTable
    -0.52
     surla
    -0.47
     vastaan
    -0.47
    帖最后由
    -0.47
    cloudflare
    -0.47
     ErrIntOverflow
    -0.46
     mobiles
    -0.45
     Sober
    -0.44
     rollen
    -0.43
     Bacchus
    -0.43
    POSITIVE LOGITS
    __*/
    0.57
     defStyleAttr
    0.56
     jScrollPane
    0.56
     AssemblyTitle
    0.54
    Hauptartikel
    0.52
     WaitForSeconds
    0.52
     TextInputType
    0.50
    SourceChecksum
    0.49
     externi
    0.49
    IEnumerator
    0.48
    Activations Density 0.501%

    No Known Activations