© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8089
    Prev
    Next
    INDEX
    Explanations

    the prefix "ins", often as the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    ins

    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
     للاسماء
    -1.05
     <<<<<<<<<<<<<<
    -1.05
     autorytatywna
    -0.99
    LookAnd
    -0.92
    \{\\
    -0.87
    ViewFeatures
    -0.87
    AsUp
    -0.84
     Roskov
    -0.82
    ResumeLayout
    -0.80
    SequentialGroup
    -0.80
    POSITIVE LOGITS
    appid
    0.40
     o
    0.38
    iestety
    0.35
    яр
    0.34
    Web
    0.33
    seiti
    0.33
    uglify
    0.33
     Web
    0.32
     O
    0.31
    առ
    0.31
    Activations Density 0.974%

    No Known Activations