INDEX

Explanations

words used in movie and TV show reviews.

oai_token-act-pair · gemini-2.0-flash

Reviews/opinions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 concorso

-0.49

 informée

-0.49

PerformLayout

-0.47

 Fair

-0.47

 释放

-0.47

pendente

-0.47

 sociaux

-0.46

verifyException

-0.45

 redor

-0.45

RemoteException

-0.45

POSITIVE LOGITS

 Cæsar

0.62

 RSSSF

0.60

RectangleBorder

0.59

 purpoſe

0.59

ArgsConstructor

0.59

 <=",

0.58



0.55

SceneManagement

0.54

帖最后由

0.54

----</

0.53

Activations Density 13.064%

words used in movie and TV show reviews.

Reviews/opinions

No Known Activations