© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15180
    Prev
    Next
    INDEX
    Explanations

    examples, especially those prefaced by abbreviations like e.g. and i.e., along with words related to food, drinks, and sweeteners

    oai_token-act-pair · gemini-2.0-flash

    food and drink

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Inscrivez
    -0.84
     Monfieur
    -0.81
     виправивши
    -0.72
     Shakspeare
    -0.71
     للاسماء
    -0.71
    ſelf
    -0.70
    IsMutable
    -0.68
    出版年
    -0.68
     Majefty
    -0.68
     Theſe
    -0.67
    POSITIVE LOGITS
    ')->
    0.60
    '],$
    0.60
    ɵɵ
    0.50
    antMatchers
    0.49
    esgue
    0.45
    CppCodeGen
    0.45
    ']->
    0.44
     dro
    0.43
    ZEN
    0.42
    erde
    0.41
    Activations Density 1.845%

    No Known Activations