INDEX

Explanations

phone numbers

oai_token-act-pair · gemini-2.0-flash

Phone numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.58

+#+#

-0.57

UnknownFields

-0.56

RegressionTest

-0.53

 Aviv

-0.52

RTEE

-0.50

}{*}{}

-0.48

CloseOperation

-0.48

/*

-0.47

BeginContext

-0.47

POSITIVE LOGITS

writeFieldEnd

0.70

providedIn

0.64

AddTagHelper

0.62

@[+][

0.55

 protoimpl

0.54

 européens

0.53

Tämä

0.52

 ComVisible

0.51

 springfox

0.51

Demografía

0.50

Activations Density 0.707%

phone numbers

Phone numbers

No Comments

No Known Activations