INDEX

Explanations

words associated with professional or academic written works, and machinery.

oai_token-act-pair · 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

SpringBootTest

-0.63

ReusableCell

-0.59

IntoConstraints

-0.54

msgTypes

-0.52

IBOutlet

-0.52

regen

-0.51

SuppressLint

-0.51

ortable

-0.50

adpleegd

-0.49

脚注の使い方

-0.49

POSITIVE LOGITS

izarse

0.64

rungsseite

0.56

 topic

0.51

topt

0.51

wnież

0.48

 theory

0.47

couz

0.46

 referenties

0.46

 transmission

0.46

Distribución

0.46

Activations Density 1.685%

words associated with professional or academic written works, and machinery.

No Comments

No Known Activations