© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    a mix of common words in different languages

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     parts
    -0.62
    styrelsen
    -0.60
     part
    -0.56
     cheval
    -0.53
    länger
    -0.51
    enterOuterAlt
    -0.50
    parts
    -0.50
     Référence
    -0.50
    BeginContext
    -0.47
     DANS
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.76
     tartalomajánló
    0.75
    SourceChecksum
    0.68
    Sucesor
    0.61
     Audiodateien
    0.59
     समीक्षाएं
    0.59
     صوتيه
    0.58
    PullParser
    0.57
     ↓,
    0.54
     Truss
    0.54
    Activations Density 0.385%

    No Known Activations