© 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. 4576
    Prev
    Next
    INDEX
    Explanations

    the word "out", sometimes with some surrounding context

    oai_token-act-pair · gemini-2.0-flash

    out

    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
     Efq
    -1.40
    MLLoader
    -1.21
     للاسماء
    -1.18
     '\\;'
    -1.16
     Jefus
    -1.16
     myſelf
    -1.16
    ſelf
    -1.13
    LookAnd
    -1.09
     Majefty
    -1.09
     Houſe
    -1.08
    POSITIVE LOGITS
     there
    0.84
     t
    0.57
    there
    0.49
     it
    0.45
     y
    0.45
     dort
    0.44
     There
    0.43
     here
    0.42
     tem
    0.41
     ther
    0.40
    Activations Density 0.463%

    No Known Activations