INDEX

Explanations

numbers and scientific publishing notation

oai_token-act-pair · gemini-2.0-flash

scientific publications

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 russes

-0.54

 variés

-0.49

 profilo

-0.48

 aanwezig

-0.46

 devraient

-0.45

 numériques

-0.45

 liggen

-0.44

 tilf

-0.44

éndolo

-0.44

 américains

-0.43

POSITIVE LOGITS

Hentet

0.72

ViewImports

0.70

onAttach

0.69

HostException

0.67

شهاد

0.66

phosa

0.66

 initComponents

0.60

HandlerContext

0.60

UnitTesting

0.60

RectangleBorder

0.59

Activations Density 31.467%

numbers and scientific publishing notation

scientific publications

No Comments

No Known Activations