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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 830
    Prev
    Next
    INDEX
    Explanations

    art-related words and words that describe landscapes or scenery, along with words related to capital punishment.

    oai_token-act-pair · gemini-2.0-flash

    forms

    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
    IntoConstraints
    -1.02
     NSCoder
    -0.68
    __(/*!
    -0.66
    GOTREF
    -0.65
    hdashline
    -0.64
    GEBURTSDATUM
    -0.64
    esModule
    -0.63
    MLLoader
    -0.62
     '\\;'
    -0.61
     Désolé
    -0.60
    POSITIVE LOGITS
     form
    1.28
     forms
    1.11
     Form
    1.07
    form
    1.02
    Form
    1.02
     Forms
    1.00
     FORM
    0.97
     forma
    0.96
     FORMS
    0.94
    Forms
    0.93
    Activations Density 3.674%

    No Known Activations