© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8256
    Prev
    Next
    INDEX
    Explanations

    modal verbs and related words of possibility or requirements, along with pronouns

    oai_token-act-pair · gemini-2.0-flash

    Fashion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WebElementEntity
    -0.79
    ChildScrollView
    -0.75
     дописавши
    -0.67
    Personendaten
    -0.62
    IVer
    -0.62
     الحره
    -0.61
    ագրություններ
    -0.60
    ApiModelProperty
    -0.60
    #+#
    -0.59
     ostavi
    -0.59
    POSITIVE LOGITS
     fashion
    1.00
    Fashion
    0.86
     drop
    0.86
     Fashion
    0.83
     dropped
    0.82
     drops
    0.81
     Drop
    0.81
    fashion
    0.81
     dropping
    0.74
    Drop
    0.74
    Activations Density 6.177%

    No Known Activations