INDEX

Explanations

dates and nearby words, and sentences describing events or items of significance

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

 GenerationType

-0.73

 kasarigan

-0.66

Revenir

-0.62

 JpaRepository

-0.59

 FetchType

-0.58

 BorderSide

-0.58

 CascadeType

-0.55

ReusableCell

-0.54

<bos>

-0.53

 الاطلاع

-0.53

POSITIVE LOGITS

Autoritní

0.81

 Pamplona

0.56

 Thebes

0.56

Tril

0.51

 Shakspeare

0.50

 Sardin

0.49

 consequence

0.47

ỗi

0.47

meric

0.47

̣ng

0.46

Activations Density 0.649%

dates and nearby words, and sentences describing events or items of significance

period

No Comments

No Known Activations