© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms, especially related to viruses, as well as text strings that look like journal citations

    oai_token-act-pair · gemini-2.0-flash

    words ending in "self"

    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
    OGND
    -1.13
    
    -1.12
     pinulongan
    -1.11
    mybatisplus
    -1.10
     resourceCulture
    -1.10
     protoimpl
    -1.10
    ंदीखरीदारी
    -1.10
    sizeCache
    -1.09
    Personendaten
    -1.08
    StoryboardSegue
    -1.05
    POSITIVE LOGITS
     itſelf
    0.17
     myſelf
    0.12
     raiſ
    0.11
     purpoſe
    0.08
     Efq
    0.06
     chofe
    0.06
     Jefus
    0.05
     pleaſure
    0.05
    ſelf
    0.05
     houſe
    0.05
    Activations Density 20.707%

    No Known Activations