© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11438
    Prev
    Next
    INDEX
    Explanations

    sentences with negative constructions using "is"

    oai_token-act-pair · gemini-2.0-flash

    negative phrases or negation

    np_token-act-pair-logits · gpt-4o-mini

    disagreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     True
    -0.81
    True
    -0.79
     true
    -0.73
    true
    -0.71
    يكب
    -0.68
    TRUE
    -0.63
    PreferredItem
    -0.62
    BufferException
    -0.60
     TRUE
    -0.60
     False
    -0.59
    POSITIVE LOGITS
    __*/
    0.53
    amaño
    0.46
    magini
    0.46
    ()];
    0.46
     cara
    0.45
    #
    0.45
     getCode
    0.45
    longer
    0.44
     استنادى
    0.44
    }`).
    0.43
    Activations Density 3.808%

    No Known Activations