INDEX

Explanations

a variety of mathematical or software-related notations.

oai_token-act-pair · gemini-2.0-flash

Code snippets with versions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Normdatei

-0.55

 saites

-0.54

 Greetings

-0.48

 Initialise

-0.47

anmoins

-0.46

llac

-0.46

 Theſe

-0.44

$($

-0.44

^^^

-0.43

 tats

-0.42

POSITIVE LOGITS

complexContent

0.77

发表于

0.69

 intptr

0.69

unmodifiable

0.68

 typelib

0.66

 CreateTagHelper

0.64

 useAppContext

0.62

立

0.61

 Chwiliwch

0.61

mybatisplus

0.60

Activations Density 3.512%

a variety of mathematical or software-related notations.

Code snippets with versions

No Comments

No Known Activations