INDEX

Explanations

information related to scientific publications, including authors, titles, and affiliations

oai_token-act-pair · gemini-2.0-flash

scientific papers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Dr

-1.05

Dr

-0.93

dr

-0.77

Drs

-0.65

dr

-0.60

 Doctor

-0.59

 OMIT

-0.56

 डॉ

-0.56

 doctor

-0.55

RenderAtEndOf

-0.55

POSITIVE LOGITS

$.

0.63

 kasarigan

0.62

 تانيه

0.57

Sucesor

0.56

发表于

0.56

 חיצוניים

0.56

".

0.52

 disappointing

0.52

 embarrassing

0.51

 Skyl

0.51

Activations Density 2.619%

information related to scientific publications, including authors, titles, and affiliations

scientific papers

No Comments

No Known Activations