© 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. 12112
    Prev
    Next
    INDEX
    Explanations

    language expressing disapproval or accusations directed at "you."

    oai_token-act-pair · gemini-2.0-flash

    Michael Forever Tribute event

    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
    ratulations
    -0.53
    duled
    -0.51
     nakalista
    -0.49
    期刊论文
    -0.47
    出版年
    -0.47
    hematical
    -0.47
     yourself
    -0.46
    ConstraintMaker
    -0.44
    badlogic
    -0.43
    structure
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.82
    GEBURTSDATUM
    0.72
    IndentedString
    0.70
    RegressionTest
    0.69
    Geplaatst
    0.68
    principalTable
    0.65
    NameInMap
    0.65
    tagext
    0.64
    MigrationBuilder
    0.60
    ]]);
    0.59
    Activations Density 0.506%

    No Known Activations