INDEX

Explanations

parts of web pages and source code

oai_token-act-pair · gemini-2.0-flash

Code and technical content

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

 Reſ

-1.13

 Diſ

-1.06

 Anſ

-1.05

 Houſe

-1.00

xase

-0.96

KommentareTeilen

-0.95

 Conſ

-0.94

 MainAxisSize

-0.94

 Perſ

-0.94

IVEREF

-0.93

POSITIVE LOGITS

men

0.52

me

0.50

re

0.50

per

0.49

0.48

 plan

0.47

os

0.47

un

0.47

 real

0.47

Activations Density 4.647%

parts of web pages and source code

Code and technical content

No Comments

No Known Activations