© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15108
    Prev
    Next
    INDEX
    Explanations

    connecting words or prepositions such as "and", "by", "in", "on", "with", or "the."

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    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
    GraphicsUnit
    -0.90
     propOrder
    -0.76
    esez
    -0.73
    +:+
    -0.72
    fjspx
    -0.66
     الحره
    -0.66
     كومونز
    -0.61
     onBind
    -0.60
     linkovi
    -0.60
    inSlope
    -0.59
    POSITIVE LOGITS
    insegna
    0.50
    ByID
    0.47
     Bretaña
    0.44
     Betten
    0.43
    ela
    0.41
     Che
    0.41
    İY
    0.40
     mad
    0.40
     Cir
    0.40
    ObjectMeta
    0.38
    Activations Density 5.837%

    No Known Activations