INDEX

Explanations

language related to government programs and administration

oai_token-act-pair · gemini-2.0-flash

Program

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.68

 שוליים

-0.66

openzeppelin

-0.60

awtextra

-0.60

 intptr

-0.59

 esternos

-0.57

 Pergamon

-0.57

InputBorder

-0.57

setVerticalGroup

-0.57

IntoConstraints

-0.57

POSITIVE LOGITS

CopyWith

0.61

 federally

0.47

 federal

0.47

=>

0.45

 Mitte

0.45

 check

0.43

بینی

0.42

 сх

0.41

projec

0.40

HomeAsUpEnabled

0.40

Activations Density 0.744%

language related to government programs and administration

Program

No Comments

No Known Activations