INDEX

Explanations

nicknames/titles

np_max-act-logits · gemini-2.0-flash

text referring to people's names and nicknames

oai_token-act-pair · gemini-2.0-flash

code or non-English speech

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.60

“

-0.56

ibar

-0.51

"__

-0.44

 called

-0.44

"-

-0.44

"_

-0.43

"`

-0.43

 “[

-0.43

``

-0.43

POSITIVE LOGITS

tagHelperRunner

0.78

 صوتيه

0.75

BeginContext

0.72

HtmlAttribute

0.71

SharedDtor

0.71

IContainer

0.69

IUrlHelper

0.69

ViewImports

0.68

 Himo

0.67

 NUKAT

0.66

Activations Density 1.081%

nicknames/titles

text referring to people's names and nicknames

code or non-English speech

No Comments

No Known Activations