INDEX

Explanations

text related to mathematical proofs by induction, summations, and set theory

oai_token-act-pair · gemini-2.0-flash

mathematical proofs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Details

-0.49

 Plan

-0.48

wap

-0.46

walla

-0.45

 détail

-0.45

︵

-0.45

fillRect

-0.44

 Titel

-0.43

즉

-0.43

 details

-0.43

POSITIVE LOGITS

 виправивши

1.01

IsMutable

0.80

 дописавши

0.73

 AssemblyCulture

0.71

 мәкалә

0.67

UnsafeEnabled

0.67

 ویکی‌پدیای

0.66

TypedDataSet

0.65

PropertyChanging

0.64

رشف

0.63

Activations Density 5.870%

text related to mathematical proofs by induction, summations, and set theory

mathematical proofs

No Comments

No Known Activations