INDEX

Explanations

foreign words

np_max-act-logits · gemini-2.0-flash

words related to sewing, particularly in a personal context.

oai_token-act-pair · 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

Autoritní

-0.66

TypedDataSet

-0.58

mem

-0.57

glPushMatrix

-0.56

sprogramm

-0.56

@[+][

-0.54

 Spisak

-0.54

 departament

-0.52

Пусть

-0.50

 cron

-0.49

POSITIVE LOGITS

IntoConstraints

0.61

 destinés

0.52

 aéri

0.52

مصادر

0.52

 typelib

0.50

 Waktu

0.49

 érz

0.48

THREADS

0.47

 destinées

0.46

fő

0.46

Activations Density 2.504%

foreign words

words related to sewing, particularly in a personal context.

No Comments

No Known Activations