INDEX

Explanations

computer-related instructions involving copying files, software, or code

oai_token-act-pair · gemini-2.0-flash

copy

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-1.11

 itſelf

-1.02

 Jefus

-1.00

 Monfieur

-0.96

^(@)

-0.96

ſelves

-0.92

 photolibrary

-0.91

 Majefty

-0.91

 Theſe

-0.91

 مشين

-0.90

POSITIVE LOGITS

0.71

0.61

 using

0.54

use

0.53

0.52

0.51

0.50

Activations Density 2.822%

computer-related instructions involving copying files, software, or code

copy

No Comments

No Known Activations