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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12439
    Prev
    Next
    INDEX
    Explanations

    words ending in "pong", "elli", or "liti" and related scientific terminology and references

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    np_max-act-logits · gemini-2.0-flash
    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
    chie
    -0.58
    ci
    -0.56
    Gio
    -0.49
     åt
    -0.48
    chia
    -0.48
     baik
    -0.46
     jornal
    -0.46
    +#+#
    -0.45
    šice
    -0.45
    anci
    -0.44
    POSITIVE LOGITS
    ResponseWriter
    0.72
    oflavin
    0.64
    ɵɵ
    0.63
    (!__
    0.59
    stateProvider
    0.58
    InteropServices
    0.58
    WebMethod
    0.57
    FormUrlEncoded
    0.56
    ScopeManager
    0.56
    PYX
    0.56
    Activations Density 0.428%

    No Known Activations