© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9235
    Prev
    Next
    INDEX
    Explanations

    code snippets or technical documentation in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash

    say "▁"

    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
     Italij
    -0.44
    ButterKnife
    -0.40
     剪影
    -0.36
     Monfieur
    -0.35
     AssemblyCompany
    -0.35
     特写
    -0.34
     Shakspeare
    -0.34
     becauſe
    -0.34
     ſeveral
    -0.33
     图解
    -0.33
    POSITIVE LOGITS
    osoba
    0.74
    Rüyada
    0.65
     ook
    0.64
    دانشنامهٔ
    0.64
     nog
    0.63
    Een
    0.63
    gemeester
    0.60
     donc
    0.60
     auch
    0.60
     een
    0.59
    Activations Density 5.389%

    No Known Activations