© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11677
    Prev
    Next
    INDEX
    Explanations

    the word "flow" referring to the movement of fluids or data, and associated words

    oai_token-act-pair · gemini-2.0-flash

    flow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     transfieras
    -0.71
    LabelTagHelper
    -0.65
    })`
    -0.58
    //};
    -0.57
    /***/
    -0.56
    LookAnd
    -0.55
    >>()
    -0.55
     Sarg
    -0.53
    })}\
    -0.53
    __))
    -0.52
    POSITIVE LOGITS
     كومونز
    0.52
     tárgy
    0.51
     integrar
    0.48
    satin
    0.47
     multer
    0.47
     ramai
    0.47
    ingtones
    0.47
    relser
    0.46
    흰색
    0.46
    اته
    0.46
    Activations Density 4.134%

    No Known Activations