© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11689
    Prev
    Next
    INDEX
    Explanations

    initials, names, dates and email addresses

    oai_token-act-pair · gemini-2.0-flash

    email addresses and names

    np_max-act · gemini-2.0-flash

    French

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     avoient
    -0.86
     fidé
    -0.83
     vectorielle
    -0.83
     étranger
    -0.81
     auroit
    -0.80
     ModelExpression
    -0.80
     enfans
    -0.78
     suprême
    -0.77
     étoient
    -0.76
     grecque
    -0.76
    POSITIVE LOGITS
    HasAnnotation
    0.54
     des
    0.53
    godic
    0.50
    jon
    0.48
    InitStruct
    0.46
     desc
    0.45
     de
    0.44
    }^{+\
    0.42
    #+#
    0.42
     CanadaChoose
    0.42
    Activations Density 4.460%

    No Known Activations