INDEX

Explanations

words related to business discussions

oai_token-act-pair · gemini-2.0-flash

gibberish tokens

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

Datuak

-0.79

 فريبيس

-0.77

 estekak

-0.72

 FetchType

-0.71

DockStyle

-0.68

УДК

-0.60

 跳转至

-0.60

AutoField

-0.59

IntoConstraints

-0.58

tvguidetime

-0.57

POSITIVE LOGITS

Архівовано

0.52

thul

0.49

 AspNetCore

0.48

tonsoft

0.47

 raised

0.47

rague

0.46

 Buff

0.46

 Butterfield

0.46

ulatus

0.45

 bust

0.45

Activations Density 1.789%

words related to business discussions

gibberish tokens

No Comments

No Known Activations