INDEX

Explanations

the pronoun "me" or "je"

oai_token-act-pair · gemini-2.0-flash

Ubuntu and Linux context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 للاسماء

-0.69

complexContent

-0.66

GEBURTSDATUM

-0.62

ngdoc

-0.53

}}^{

-0.51

 orar

-0.50

 Aktion

-0.49

 ✭✭

-0.49

balleur

-0.49

SerializedName

-0.49

POSITIVE LOGITS

 naselje

0.59

comuna

0.54

 setuptools

0.50

mergeFrom

0.49

Nar

0.49

ynos

0.49

!*\

0.47

Jawa

0.47

Throwaway

0.46

Nar

0.46

Activations Density 0.253%

the pronoun "me" or "je"

Ubuntu and Linux context

No Comments

No Known Activations