© 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. 7130
    Prev
    Next
    INDEX
    Explanations

    various prepositions and conjunctions that often appear after nouns

    oai_token-act-pair · gemini-2.0-flash

    Programming code comments

    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
     orientations
    -0.67
     quæ
    -0.65
     dissemination
    -0.63
     precursors
    -0.56
     emulsions
    -0.56
    hips
    -0.56
     portfolios
    -0.55
     voeten
    -0.55
     implantation
    -0.54
     tolerances
    -0.54
    POSITIVE LOGITS
    adpleegd
    0.53
    hallo
    0.46
     wol
    0.46
     <<<<<<<<<<<<<<
    0.46
     the
    0.45
     gynhyrchwyd
    0.42
    IntoConstraints
    0.42
     ses
    0.41
    LookAnd
    0.41
     Besøkt
    0.41
    Activations Density 5.544%

    No Known Activations