© 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. 9397
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and certain prepositions and conjunctions adjacent to numbers (it is possible it also responds to the start of digits: 1, 2, 3 etc.)

    oai_token-act-pair · gemini-2.0-flash

    Technical reports

    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
    ্ত
    -0.56
     newOwner
    -0.48
     X
    -0.47
     ninety
    -0.46
     val
    -0.45
     x
    -0.44
     发表于
    -0.42
     nine
    -0.42
     sixty
    -0.42
    Liên
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.64
    AdapterView
    0.64
    ⓧ
    0.64
     rospy
    0.63
    ResumeLayout
    0.59
     onBind
    0.58
     createSlice
    0.57
    enterOuterAlt
    0.56
    1
    0.56
    DESTROY
    0.55
    Activations Density 6.914%

    No Known Activations