© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10818
    Prev
    Next
    INDEX
    Explanations

    the suffix "hip" as an ending

    oai_token-act-pair · gemini-2.0-flash

    hip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ism
    -0.84
    st
    -0.64
    ment
    -0.61
     CanadaChoose
    -0.58
    h
    -0.57
    des
    -0.57
    es
    -0.56
    de
    -0.53
    div
    -0.52
    para
    -0.52
    POSITIVE LOGITS
    yntaxException
    1.02
     referenties
    1.02
     feroit
    0.91
     éditoriale
    0.91
    TemporalType
    0.90
     Investigaciones
    0.88
    iented
    0.85
     étoient
    0.83
    EDEFAULT
    0.83
    }))
    0.81
    Activations Density 0.699%

    No Known Activations