© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12572
    Prev
    Next
    INDEX
    Explanations

    high numbers of high frequency words

    oai_token-act-pair · gemini-2.0-flash

    plans and hopes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     resourceCulture
    -0.61
    Попис
    -0.54
    RTLR
    -0.53
    })]
    -0.48
     ostavi
    -0.47
    ItemBackground
    -0.46
    öfe
    -0.46
    agré
    -0.46
    culares
    -0.46
     lect
    -0.45
    POSITIVE LOGITS
     plans
    1.90
     hopes
    1.67
    plans
    1.55
     Plans
    1.53
    Plans
    1.52
     PLANS
    1.45
     Pläne
    1.30
     dreams
    1.17
     ambitions
    1.16
     aspirations
    1.13
    Activations Density 5.472%

    No Known Activations