INDEX

Explanations

first person pronouns or words typically found in advertisements

oai_token-act-pair · gemini-2.0-flash

period

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

@"

-0.44

MessageTagHelper

-0.44

 Governor

-0.42

pat

-0.42

-0.41

 Qual

-0.41

Red

-0.41

TAWA

-0.41

Map

-0.40

anga

-0.40

POSITIVE LOGITS

erdings

0.67

WithMany

0.66

 houſe

0.66

 purpoſe

0.63

GraphicsUnit

0.63

клопе

0.63

 poffe

0.60

]--;

0.60

 occaf

0.59

 ſtate

0.57

Activations Density 0.229%

first person pronouns or words typically found in advertisements

period

No Comments

No Known Activations