INDEX

Explanations

sentences describing product features, construction, and compatibility using the word 'is'

oai_token-act-pair · gemini-2.0-flash

is/are

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

sidemargin

-0.55

 quelcon

-0.54

nhof

-0.54

MutableLiveData

-0.51

élève

-0.50

Manbalar

-0.50

 kesan

-0.48

 spesa

-0.47

تقاوى

-0.47

 élèves

-0.47

POSITIVE LOGITS

yntaxException

0.73

 constructed

0.60

aarrggbb

0.59

WireFormatLite

0.59

 manufactured

0.59

ThroughAttribute

0.57

IUrlHelper

0.55

 Numerade

0.55

<!--[

0.54

verwijspagina

0.53

Activations Density 1.139%

sentences describing product features, construction, and compatibility using the word 'is'

is/are

No Comments

No Known Activations