INDEX

Explanations

descriptions of eating and drinking

oai_token-act-pair · gemini-2.0-flash

alcohol and drinking

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

LoadScene

-0.50

 vĩnh

-0.48

flashdata

-0.47

ChildScrollView

-0.46

lask

-0.45

moveToFirst

-0.44

 Beverage

-0.44

glPopMatrix

-0.43

orsa

-0.43

isNullOrEmpty

-0.43

POSITIVE LOGITS

ⓧ

0.62

 poveznice

0.61

CodedInputStream

0.60

psack

0.58

FieldBuilder

0.56

 corporal

0.56

 Roskov

0.56

Zeneca

0.52

oredCriteria

0.52

 Wicidata

0.51

Activations Density 1.274%

descriptions of eating and drinking

alcohol and drinking

No Comments

No Known Activations