© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11307
    Prev
    Next
    INDEX
    Explanations

    mentions of two distinct concepts relative to each other

    oai_token-act-pair · gemini-2.0-flash

    other/another

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     EconPapers
    -0.75
    adpleegd
    -0.71
    SourceChecksum
    -0.66
    EDEFAULT
    -0.65
    期刊论文
    -0.64
     Roskov
    -0.62
    #+#
    -0.61
     useStyles
    -0.61
     Exactos
    -0.60
    ksikon
    -0.60
    POSITIVE LOGITS
    ida
    0.47
    ModelAndView
    0.46
    msgTypes
    0.46
    })));
    0.44
    ref
    0.41
     who
    0.40
    real
    0.40
    ={`${
    0.40
     שוליים
    0.40
    ote
    0.39
    Activations Density 1.355%

    No Known Activations